Accenture Generative AI Primers PDF

7/16/24, 11:01 PM Introduction to Generative AI - Pre quiz: Attempt review   Dashboard / Primer 2.0 - App Dev / Stage 1 / Gen AI / Introduction to Generative AI Quiz review Started on Tuesday, 16 July 2024, 10...

7/16/24, 11:01 PM Introduction to Generative AI - Pre quiz: Attempt review   Dashboard / Primer 2.0 - App Dev / Stage 1 / Gen AI / Introduction to Generative AI Quiz review Started on Tuesday, 16 July 2024, 10:52 PM State Finished Completed on Tuesday, 16 July 2024, 11:00 PM Time taken 8 mins 39 secs Marks 8.00/10.00 Grade 80.00 out of 100.00 Question 1 Incorrect Mark 0.00 out of 1.00 What distinguishes Generative AI from Discriminative AI? 57125 Generative focuses on labeling, Discriminative on generating Generative models data distribution, while Discriminative models the boundary between classes Both are the same  Generative is for images, Discriminative for text Generative is older, Discriminative is newer The correct answer is: Generative models data distribution, while Discriminative models the boundary between classes Question 2 Correct Mark 1.00 out of 1.00 57125 What does AI stand for? Advanced Integration Automated Information Automated Interaction Application Interface Artificial Intelligence The correct answer is: Artificial Intelligence 57125 https://accenturelearning.tekstac.com/mod/quiz/review.php?attempt=2946108&cmid=3666 1/4 7/16/24, 11:01 PM Introduction to Generative AI - Pre quiz: Attempt review Question 3 Incorrect Mark 0.00 out of 1.00 Which of the following fields can utilize Generative AI to create new, original content or simulations? Transportation Art and Music Banking Data Analysis  E-commerce The correct answer is: Art and Music Question 4 Correct Mark 1.00 out of 1.00 57125 Generative AI is closely related to which type of models? Generative models Classification models Decision trees Clustering models Regression models The correct answer is: Generative models 57125 Question 5 Correct Mark 1.00 out of 1.00 Which statement best defines Generative AI? AI that can generate new data samples AI that automates repetitive tasks 57125 AI that predicts future trends AI that understands human emotions AI that classifies data The correct answer is: AI that can generate new data samples https://accenturelearning.tekstac.com/mod/quiz/review.php?attempt=2946108&cmid=3666 2/4 7/16/24, 11:01 PM Introduction to Generative AI - Pre quiz: Attempt review Question 6 Correct Mark 1.00 out of 1.00 Which of the following is a real-world example of Generative AI? Sorting emails Translating languages Predicting stock market prices Generating realistic human faces in movies Automating cars The correct answer is: Generating realistic human faces in movies Question 7 Correct Mark 1.00 out of 1.00 57125 Which type of AI is primarily concerned with how data is generated rather than how it's separated? Discriminative AI Generative AI Reinforcement Learning Supervised Learning Unsupervised Learning The correct answer is: Generative AI 57125 Question 8 Correct Mark 1.00 out of 1.00 Which AI type primarily focuses on labeling data? Generative AI Semi-supervised AI 57125 Reinforcement AI Regression AI Supervised AI The correct answer is: Supervised AI https://accenturelearning.tekstac.com/mod/quiz/review.php?attempt=2946108&cmid=3666 3/4 7/16/24, 11:01 PM Introduction to Generative AI - Pre quiz: Attempt review Question 9 Correct Mark 1.00 out of 1.00 Which of the following is NOT a type of AI? Generative AI Reinforcement AI Supervised AI Generative Art Unsupervised AI The correct answer is: Generative Art Question 10 Correct Mark 1.00 out of 1.00 57125 In which application is Generative AI NOT typically used? Designing virtual environments Generating music Producing realistic video game characters Automating customer service chats Creating art 57125 The correct answer is: Automating customer service chats Jump to... Introduction to Generative AI ► 57125 https://accenturelearning.tekstac.com/mod/quiz/review.php?attempt=2946108&cmid=3666 4/4 7/16/24, 11:11 PM Introduction to Generative AI - Post quiz: Attempt review   Dashboard / Primer 2.0 - App Dev / Stage 1 / Gen AI / Introduction to Generative AI Quiz review Started on Tuesday, 16 July 2024, 11:06 PM State Finished Completed on Tuesday, 16 July 2024, 11:10 PM Time taken 4 mins 37 secs Marks 10.00/10.00 Grade 100.00 out of 100.00 Question 1 Correct Mark 1.00 out of 1.00 How does Generative AI differ from Classification AI? It requires more data It's easier to implement 57125 It generates new data rather than categorizing existing data It's more accurate It's faster The correct answer is: It generates new data rather than categorizing existing data Question 2 Correct Mark 1.00 out of 1.00 57125 Why is Generative AI considered significant in the realm of artificial intelligence? It reduces the need for large datasets It can produce new, previously unseen data samples It speeds up training processes It simplifies complex algorithms It exclusively works with images 57125 The correct answer is: It can produce new, previously unseen data samples https://accenturelearning.tekstac.com/mod/quiz/review.php?attempt=2946433&cmid=3667 1/4 7/16/24, 11:11 PM Introduction to Generative AI - Post quiz: Attempt review Question 3 Correct Mark 1.00 out of 1.00 If an AI system is designed to label images of cats and dogs, it is primarily a _______ model. Reinforcement Discriminative Generative Hybrid Unsupervised The correct answer is: Discriminative Question 4 Correct Mark 1.00 out of 1.00 57125 What is Generative AI primarily used for? Data labeling Generating new data Classification Optimization Regression The correct answer is: Generating new data 57125 Question 5 Correct Mark 1.00 out of 1.00 Generative AI can be used to create which of the following? New artworks and music pieces Classification categories 57125 Regression models Data labels Decision boundaries The correct answer is: New artworks and music pieces https://accenturelearning.tekstac.com/mod/quiz/review.php?attempt=2946433&cmid=3667 2/4 7/16/24, 11:11 PM Introduction to Generative AI - Post quiz: Attempt review Question 6 Correct Mark 1.00 out of 1.00 Which is NOT a real-world application of Generative AI? Generating game environments Producing synthetic voices Creating virtual fashion designs Deepfake videos Predicting stock market prices The correct answer is: Predicting stock market prices Question 7 Correct Mark 1.00 out of 1.00 57125 Which of the following is a direct application of Generative AI in the entertainment industry? Recommending movies to users Automating video editing Predicting movie success Creating realistic CGI characters Translating movie scripts 57125 The correct answer is: Creating realistic CGI characters Question 8 Correct Mark 1.00 out of 1.00 Which AI type is best for predicting outcomes? Semi-supervised AI Regression AI 57125 Generative AI Classification AI Reinforcement AI The correct answer is: Regression AI https://accenturelearning.tekstac.com/mod/quiz/review.php?attempt=2946433&cmid=3667 3/4 7/16/24, 11:11 PM Introduction to Generative AI - Post quiz: Attempt review Question 9 Correct Mark 1.00 out of 1.00 Which statement best describes the role of Generative AI? It is the oldest form of AI It is exclusively used in robotics It is primarily used for data sorting It is best suited for regression tasks It focuses on generating data based on learned patterns The correct answer is: It focuses on generating data based on learned patterns Question 10 Correct Mark 1.00 out of 1.00 57125 In the context of AI, which model type is more concerned with the underlying distribution of data? Regression AI Hybrid AI Generative AI Reinforcement AI Classification AI The correct answer is: Generative AI 57125 ◄ Introduction to Generative AI Jump to... Case Study - GEN AI in Fashion ► 57125 https://accenturelearning.tekstac.com/mod/quiz/review.php?attempt=2946433&cmid=3667 4/4 7/16/24, 11:43 PM Case Study - GEN AI in Fashion - Quiz: Attempt review   Dashboard / Primer 2.0 - App Dev / Stage 1 / Gen AI / Introduction to Generative AI Quiz review Started on Tuesday, 16 July 2024, 11:11 PM State Finished Completed on Tuesday, 16 July 2024, 11:43 PM Time taken 31 mins 33 secs Marks 14.00/15.00 Grade 93.33 out of 100.00 Question 1 Correct Mark 1.00 out of 1.00 Which is a potential future application of Generative AI in fashion? Virtual reality games 57125 Hyper-personalized clothing Virtual cooking shows AI-driven music composition Space exploration The correct answer is: Hyper-personalized clothing Question 2 Incorrect Mark 0.00 out of 1.00 57125 Beyond body image standards, what's another ethical concern regarding virtual models? The potential for AI to replace all human jobs in fashion The potential for AI to create biased designs The potential for AI to misuse personal data The potential for AI to create unrealistic beauty standards  The authenticity of virtual influencers in advertising campaigns 57125 The correct answer is: The authenticity of virtual influencers in advertising campaigns https://accenturelearning.tekstac.com/mod/quiz/review.php?attempt=2946586&cmid=3668 1/6 7/16/24, 11:43 PM Case Study - GEN AI in Fashion - Quiz: Attempt review Question 3 Correct Mark 1.00 out of 1.00 What is a potential challenge of over-relying on AI in fashion? Overproduction of garments Reduced customer engagement Decreased sales Overshadowing human creativity and intuition Reduced data availability The correct answer is: Overshadowing human creativity and intuition Question 4 Correct Mark 1.00 out of 1.00 57125 Why might there be concerns about an over-reliance on data-driven AI in fashion? AI can operate 24/7 without breaks AI can predict future fashion trends with certainty Fashion inherently values human creativity and intuition AI can process data faster than humans AI can store more data than human memory 57125 The correct answer is: Fashion inherently values human creativity and intuition Question 5 Correct Mark 1.00 out of 1.00 In the context of sustainability, how might AI be used in material design? By enhancing fabric softness By creating more colorful fabrics 57125 By making fabrics more elastic By simulating and designing eco-friendly materials By making fabrics waterproof The correct answer is: By simulating and designing eco-friendly materials https://accenturelearning.tekstac.com/mod/quiz/review.php?attempt=2946586&cmid=3668 2/6 7/16/24, 11:43 PM Case Study - GEN AI in Fashion - Quiz: Attempt review Question 6 Correct Mark 1.00 out of 1.00 Which brand has utilized AI for generating new clothing designs? Gucci Zara StitchFix Prada H&M The correct answer is: StitchFix Question 7 Correct Mark 1.00 out of 1.00 57125 How might AI transform the fitting experience in fashion retail? By offering a faster checkout process By providing a 3D view of the store By playing AI-generated music in fitting rooms By offering discounts during fittings By allowing customers to virtually "try on" clothes 57125 The correct answer is: By allowing customers to virtually "try on" clothes Question 8 Correct Mark 1.00 out of 1.00 How can Generative AI contribute to sustainable fashion? By increasing production rates By predicting weather patterns 57125 By enhancing e-commerce platforms By designing video games By designing sustainable fabrics The correct answer is: By designing sustainable fabrics https://accenturelearning.tekstac.com/mod/quiz/review.php?attempt=2946586&cmid=3668 3/6 7/16/24, 11:43 PM Case Study - GEN AI in Fashion - Quiz: Attempt review Question 9 Correct Mark 1.00 out of 1.00 What ethical concern arises from the use of virtual models in fashion? Concerns about AI taking over the world Concerns about AI and electricity consumption Concerns about AI replacing fashion designers Questions about body image standards and job losses for human models Concerns about AI creating unfashionable designs The correct answer is: Questions about body image standards and job losses for human models Question 10 Correct Mark 1.00 out of 1.00 57125 What could be a futuristic application of Generative AI in creating personalized clothing? By analyzing global fashion trends By considering the majority's preferences By designing clothing based on an individual's mood By creating seasonal collections By replicating popular celebrity styles 57125 The correct answer is: By designing clothing based on an individual's mood Question 11 Correct Mark 1.00 out of 1.00 How does AI enhance the shopping experience? By providing personalized product recommendations By offering discounts 57125 By improving website speed By increasing product variety By offering virtual games The correct answer is: By providing personalized product recommendations https://accenturelearning.tekstac.com/mod/quiz/review.php?attempt=2946586&cmid=3668 4/6 7/16/24, 11:43 PM Case Study - GEN AI in Fashion - Quiz: Attempt review Question 12 Correct Mark 1.00 out of 1.00 How can Generative AI potentially impact inventory management in fashion? By increasing the speed of garment production By enhancing e-commerce platforms By designing new storage systems By reducing the cost of materials By predicting fashion trends with higher accuracy The correct answer is: By predicting fashion trends with higher accuracy Question 13 Correct Mark 1.00 out of 1.00 57125 What aspect of AI in fashion raises concerns about user privacy? Personalized shopping experiences AI-generated music Virtual fashion shows Virtual reality games AI-driven automobiles 57125 The correct answer is: Personalized shopping experiences Question 14 Correct Mark 1.00 out of 1.00 What is the global valuation of the fashion industry? $3 trillion $5 trillion 57125 $2.5 trillion $500 billion $1 trillion The correct answer is: $2.5 trillion https://accenturelearning.tekstac.com/mod/quiz/review.php?attempt=2946586&cmid=3668 5/6 7/16/24, 11:43 PM Case Study - GEN AI in Fashion - Quiz: Attempt review Question 15 Correct Mark 1.00 out of 1.00 Who is a prominent virtual influencer mentioned in the case study? Naomi Campbell Gigi Hadid Lil Miquela Kylie Jenner Bella Hadid The correct answer is: Lil Miquela ◄ Case Study - GEN AI in Fashion Jump to... 57125 Brief History of Generative AI - Pre Quiz ► 57125 57125 https://accenturelearning.tekstac.com/mod/quiz/review.php?attempt=2946586&cmid=3668 6/6 7/16/24, 11:51 PM Brief History of Generative AI - Pre Quiz: Attempt review   Dashboard / Primer 2.0 - App Dev / Stage 1 / Gen AI / Brief History of Generative AI Quiz review Started on Tuesday, 16 July 2024, 11:47 PM State Finished Completed on Tuesday, 16 July 2024, 11:51 PM Time taken 3 mins 39 secs Marks 10.00/10.00 Grade 100.00 out of 100.00 Question 1 Correct Mark 1.00 out of 1.00 Who introduced Generative Adversarial Networks (GANs)? Yann LeCun Andrew Ng 57125 Geoffrey Hinton Ian Goodfellow Yoshua Bengio The correct answer is: Ian Goodfellow Question 2 Correct Mark 1.00 out of 1.00 57125 What are the two main components of a GAN? Forward and Backward Input and Output Generator and Discriminator None of the given options Encoder and Decoder The correct answer is: Generator and Discriminator 57125 https://accenturelearning.tekstac.com/mod/quiz/review.php?attempt=2947406&cmid=3670 1/4 7/16/24, 11:51 PM Brief History of Generative AI - Pre Quiz: Attempt review Question 3 Correct Mark 1.00 out of 1.00 Which model marked a significant milestone in the use of transformers in NLP? BERT LSTM GAN RNN CNN The correct answer is: BERT Question 4 Correct Mark 1.00 out of 1.00 57125 Which model uses a probabilistic approach to encode and decode data? DCGAN BigGAN CycleGAN VAE Transformer The correct answer is: VAE 57125 Question 5 Correct Mark 1.00 out of 1.00 Which pioneering research in Generative AI specifically emphasized the generation of text sequences? "DeepFace: Closing the Gap to Human-Level Performance in Face Recognition" "A Neural Algorithm of Artistic Style" 57125 "Understanding Machine Learning: From Theory to Algorithms" "Visualizing and Understanding Convolutional Networks" "Sequence to Sequence Learning with Neural Networks" The correct answer is: "Sequence to Sequence Learning with Neural Networks" https://accenturelearning.tekstac.com/mod/quiz/review.php?attempt=2947406&cmid=3670 2/4 7/16/24, 11:51 PM Brief History of Generative AI - Pre Quiz: Attempt review Question 6 Correct Mark 1.00 out of 1.00 Which of the following is NOT a direct application of GANs but rather an outcome of its influence? Style transfer Image-to-Image translation Reinforcement learning in game playing Generating realistic images Super-resolution The correct answer is: Reinforcement learning in game playing Question 7 Correct Mark 1.00 out of 1.00 57125 What is the primary purpose of generative models? None of the given options Classifying data Generating new data Filtering data Recognizing patterns The correct answer is: Generating new data 57125 Question 8 Correct Mark 1.00 out of 1.00 Which of the following research papers is foundational for Variational Autoencoders (VAEs)? "Mastering Chess and Shogi by Self-Play" "Deep Residual Learning for Image Recognition" 57125 "Auto-Encoding Variational Bayes" "Attention is All You Need" "Generative Adversarial Nets" The correct answer is: "Auto-Encoding Variational Bayes" https://accenturelearning.tekstac.com/mod/quiz/review.php?attempt=2947406&cmid=3670 3/4 7/16/24, 11:51 PM Brief History of Generative AI - Pre Quiz: Attempt review Question 9 Correct Mark 1.00 out of 1.00 In which year were Generative Adversarial Networks (GANs) first introduced? 2014 2010 2012 2016 2018 The correct answer is: 2014 Question 10 Correct Mark 1.00 out of 1.00 57125 Which architecture is primarily associated with attention mechanisms? Transformer GAN CNN VAE RNN The correct answer is: Transformer 57125 ◄ Case Study - GEN AI in Fashion - Quiz Jump to... Brief History of Generative AI ► 57125 https://accenturelearning.tekstac.com/mod/quiz/review.php?attempt=2947406&cmid=3670 4/4 7/17/24, 12:26 AM Brief History of Generative AI - Post Quiz: Attempt review   Dashboard / Primer 2.0 - App Dev / Stage 1 / Gen AI / Brief History of Generative AI Quiz review Started on Wednesday, 17 July 2024, 12:20 AM State Finished Completed on Wednesday, 17 July 2024, 12:26 AM Time taken 6 mins 28 secs Marks 9.00/10.00 Grade 90.00 out of 100.00 Question 1 Correct Mark 1.00 out of 1.00 What is the primary advantage of Transformers over RNNs in terms of processing sequences? 57125 Better attention mechanism Parallel Processing Faster convergence None of the given options More parameters The correct answer is: Parallel Processing Question 2 Correct Mark 1.00 out of 1.00 57125 In the context of GANs, what is the role of the Discriminator? To distinguish between real and generated data To generate data To encode data To transform data To decode data 57125 The correct answer is: To distinguish between real and generated data https://accenturelearning.tekstac.com/mod/quiz/review.php?attempt=2947935&cmid=3675 1/4 7/17/24, 12:26 AM Brief History of Generative AI - Post Quiz: Attempt review Question 3 Correct Mark 1.00 out of 1.00 Which AI model series by OpenAI, based on the Transformer architecture, is known for generating highly coherent content? TransformerXL BERT ResNet GPT series CycleGAN The correct answer is: GPT series Question 4 Correct Mark 1.00 out of 1.00 57125 Which model is known for its rules for creating stable and effective AI image-makers? CycleGAN Transformer DCGAN VAE BigGAN The correct answer is: DCGAN 57125 Question 5 Incorrect Mark 0.00 out of 1.00 Which of the following is NOT a direct application of the Transformer architecture? Image recognition Text summarization 57125 Image generation  Question answering Text translation The correct answer is: Image recognition https://accenturelearning.tekstac.com/mod/quiz/review.php?attempt=2947935&cmid=3675 2/4 7/17/24, 12:26 AM Brief History of Generative AI - Post Quiz: Attempt review Question 6 Correct Mark 1.00 out of 1.00 What mechanism allows the Transformer model to weigh the importance of different words in a sequence? Self-Attention Mechanism Encoding Mechanism None of the given options Decoding Mechanism Recurrent Mechanism The correct answer is: Self-Attention Mechanism Question 7 Correct Mark 1.00 out of 1.00 57125 What is the main innovation introduced by the "Attention Is All You Need" paper? Introduction of GANs Transformer architecture Introduction of VAEs Introduction of RNNs Introduction of CNNs 57125 The correct answer is: Transformer architecture Question 8 Correct Mark 1.00 out of 1.00 Which generative model introduced a stochastic layer that models data in a latent space? VAE BigGAN 57125 Transformer CycleGAN DCGAN The correct answer is: VAE https://accenturelearning.tekstac.com/mod/quiz/review.php?attempt=2947935&cmid=3675 3/4 7/17/24, 12:26 AM Brief History of Generative AI - Post Quiz: Attempt review Question 9 Correct Mark 1.00 out of 1.00 Which model can transform horse photos into zebra photos without direct comparison? DCGAN BigGAN CycleGAN Transformer VAE The correct answer is: CycleGAN Question 10 Correct Mark 1.00 out of 1.00 57125 Which model demonstrated that using larger architectures can produce better images? CycleGAN BigGAN DCGAN Transformer VAE The correct answer is: BigGAN 57125 ◄ Additional Reading 3 - Transformers Jump to... Fundamentals of ML - Pre Quiz ► 57125 https://accenturelearning.tekstac.com/mod/quiz/review.php?attempt=2947935&cmid=3675 4/4 7/17/24, 12:32 AM Fundamentals of ML - Pre Quiz: Attempt review   Dashboard / Primer 2.0 - App Dev / Stage 1 / Gen AI / Fundamentals of Machine Learning and Neural Networks Quiz review Started on Wednesday, 17 July 2024, 12:27 AM State Finished Completed on Wednesday, 17 July 2024, 12:32 AM Time taken 4 mins 56 secs Marks 10.00/10.00 Grade 100.00 out of 100.00 Question 1 Correct Mark 1.00 out of 1.00 Which activation function outputs a value between 0 and 1? 57125 Rectified Linear Unit (ReLU) Hyperbolic Tangent (tanh) Sigmoid Linear Leaky ReLU The correct answer is: Sigmoid Question 2 Correct Mark 1.00 out of 1.00 57125 What is the main difference between regression and classification? Regression is unsupervised Classification is unsupervised Regression uses labeled data, Classification doesn't Regression predicts a continuous output, Classification predicts a discrete label Both are the same 57125 The correct answer is: Regression predicts a continuous output, Classification predicts a discrete label https://accenturelearning.tekstac.com/mod/quiz/review.php?attempt=2948054&cmid=3676 1/4 7/17/24, 12:32 AM Fundamentals of ML - Pre Quiz: Attempt review Question 3 Correct Mark 1.00 out of 1.00 What is the primary goal of machine learning? To design new algorithms To increase computational speed To allow computers to learn from data None of the given options To program explicit rules for a task The correct answer is: To allow computers to learn from data Question 4 Correct Mark 1.00 out of 1.00 57125 Which of the following is NOT a common machine learning algorithm? Neural Networks Decision Trees Quantum Entanglement Support Vector Machines K-Means Clustering The correct answer is: Quantum Entanglement 57125 Question 5 Correct Mark 1.00 out of 1.00 What is the primary purpose of a loss function in training neural networks? To activate neurons To speed up training 57125 To define the network's architecture To quantify the difference between predicted and actual values To initialize weights The correct answer is: To quantify the difference between predicted and actual values https://accenturelearning.tekstac.com/mod/quiz/review.php?attempt=2948054&cmid=3676 2/4 7/17/24, 12:32 AM Fundamentals of ML - Pre Quiz: Attempt review Question 6 Correct Mark 1.00 out of 1.00 In the context of neural networks, what does the term "backpropagation" refer to? The initial random assignment of weights The method of adjusting weights based on the error The forward flow of data The process of adding more layers The activation of neurons in the hidden layer The correct answer is: The method of adjusting weights based on the error Question 7 Correct Mark 1.00 out of 1.00 57125 Which application of ML is used to group similar items? Classification Clustering Regression Ranking Recommendation The correct answer is: Clustering 57125 Question 8 Correct Mark 1.00 out of 1.00 Which of the following is a technique to prevent overfitting in neural networks? Dropout Learning Rate Adjustment 57125 Gradient Clipping Using a larger dataset Increasing the number of layers The correct answer is: Dropout https://accenturelearning.tekstac.com/mod/quiz/review.php?attempt=2948054&cmid=3676 3/4 7/17/24, 12:32 AM Fundamentals of ML - Pre Quiz: Attempt review Question 9 Correct Mark 1.00 out of 1.00 Which component of a neural network is responsible for combining inputs and passing them to the next layer? Bias Neuron (or Node) Layer Weight Activation Function The correct answer is: Neuron (or Node) Question 10 Correct Mark 1.00 out of 1.00 57125 Which of the following is NOT a type of machine learning? Recursive Learning Semi-supervised Learning Unsupervised Learning Reinforcement Learning Supervised Learning The correct answer is: Recursive Learning 57125 ◄ Brief History of Generative AI - Post Quiz Jump to... Fundamentals of Machine Learning and Neural Networks ► 57125 https://accenturelearning.tekstac.com/mod/quiz/review.php?attempt=2948054&cmid=3676 4/4 7/17/24, 12:43 AM Fundamentals of ML - Post Quiz: Attempt review   Dashboard / Primer 2.0 - App Dev / Stage 1 / Gen AI / Fundamentals of Machine Learning and Neural Networks Quiz review Started on Wednesday, 17 July 2024, 12:39 AM State Finished Completed on Wednesday, 17 July 2024, 12:42 AM Time taken 3 mins 50 secs Marks 10.00/10.00 Grade 100.00 out of 100.00 Question 1 Correct Mark 1.00 out of 1.00 Which function introduces non-linearity in a neural network? Weight Function Bias Function 57125 Activation Function Loss Function Linear Function The correct answer is: Activation Function Question 2 Correct Mark 1.00 out of 1.00 57125 In a neural network, what does a neuron compute? The gradient of the loss The error of the network A weighted sum followed by an activation function A fixed value The learning rate 57125 The correct answer is: A weighted sum followed by an activation function https://accenturelearning.tekstac.com/mod/quiz/review.php?attempt=2948183&cmid=3677 1/4 7/17/24, 12:43 AM Fundamentals of ML - Post Quiz: Attempt review Question 3 Correct Mark 1.00 out of 1.00 How is a neural network's performance typically evaluated during training? Using the training data Using the weights Using a validation set Using the activation functions Using the test data The correct answer is: Using a validation set Question 4 Correct Mark 1.00 out of 1.00 57125 In which type of ML does an agent learn by interacting with an environment? Regression Clustering Unsupervised Learning Reinforcement Learning Supervised Learning The correct answer is: Reinforcement Learning 57125 Question 5 Correct Mark 1.00 out of 1.00 Which of the following is a challenge in training deep neural networks? All neurons activating at once Vanishing/Exploding gradients 57125 Linear activation functions Small datasets Too few neurons The correct answer is: Vanishing/Exploding gradients https://accenturelearning.tekstac.com/mod/quiz/review.php?attempt=2948183&cmid=3677 2/4 7/17/24, 12:43 AM Fundamentals of ML - Post Quiz: Attempt review Question 6 Correct Mark 1.00 out of 1.00 Which of the following is a common activation function in neural networks? ReLU (Rectified Linear Unit) Linear Function Polynomial Function Bias Activation Weighted Sum The correct answer is: ReLU (Rectified Linear Unit) Question 7 Correct Mark 1.00 out of 1.00 57125 Which of the following is NOT a layer type in a typical neural network? Output Layer Quantum Layer Input Layer Convolutional Layer Hidden Layer The correct answer is: Quantum Layer 57125 Question 8 Correct Mark 1.00 out of 1.00 Which application of ML is used to detect unusual patterns in data? Anomaly Detection Classification 57125 Ranking Regression Clustering The correct answer is: Anomaly Detection https://accenturelearning.tekstac.com/mod/quiz/review.php?attempt=2948183&cmid=3677 3/4 7/17/24, 12:43 AM Fundamentals of ML - Post Quiz: Attempt review Question 9 Correct Mark 1.00 out of 1.00 What is the primary purpose of backpropagation? Adjusting weights based on the error Initialization of weights Data preprocessing Forward propagation of data Activation of neurons The correct answer is: Adjusting weights based on the error Question 10 Correct Mark 1.00 out of 1.00 57125 What is the role of the loss function in training a neural network? To initialize the weights To quantify the difference between predicted and actual values To activate the neurons To introduce non-linearity To define the network architecture 57125 The correct answer is: To quantify the difference between predicted and actual values ◄ Fundamentals of Machine Learning and Neural Networks Jump to... Introduction to Generative Models - Pre Quiz ► 57125 https://accenturelearning.tekstac.com/mod/quiz/review.php?attempt=2948183&cmid=3677 4/4 7/17/24, 12:47 AM Introduction to Generative Models - Pre Quiz: Attempt review   Dashboard / Primer 2.0 - App Dev / Stage 1 / Gen AI / Introduction to Generative Models Quiz review Started on Wednesday, 17 July 2024, 12:43 AM State Finished Completed on Wednesday, 17 July 2024, 12:47 AM Time taken 4 mins Marks 10.00/10.00 Grade 100.00 out of 100.00 Question 1 Correct Mark 1.00 out of 1.00 Which of the following is NOT a generative model? Support Vector Machines57125 Restricted Boltzmann Machines Gaussian Mixture Models Variational Autoencoders Generative Adversarial Networks The correct answer is: Support Vector Machines Question 2 Correct Mark 1.00 out of 1.00 57125 Which of the following is crucial for understanding the behavior of generative models? Convolutional layers Activation functions Probability distributions and likelihood Backpropagation Gradient descent 57125 The correct answer is: Probability distributions and likelihood https://accenturelearning.tekstac.com/mod/quiz/review.php?attempt=2948245&cmid=3678 1/4 7/17/24, 12:47 AM Introduction to Generative Models - Pre Quiz: Attempt review Question 3 Correct Mark 1.00 out of 1.00 Which model type is primarily concerned with determining P(y | x)? Both Generative and Discriminative Discriminative Model Generative Model Probability Distribution Bayesian model The correct answer is: Discriminative Model Question 4 Correct Mark 1.00 out of 1.00 57125 Generative models are primarily used for which of the following tasks? Regression Clustering Classification Reinforcement learning Generating new data samples similar to the input data 57125 The correct answer is: Generating new data samples similar to the input data Question 5 Correct Mark 1.00 out of 1.00 What does likelihood measure in the context of a model? The generative capacity of the model The complexity of the model 57125 The error rate of the model How well the model explains the observed data The probability of the model being correct The correct answer is: How well the model explains the observed data https://accenturelearning.tekstac.com/mod/quiz/review.php?attempt=2948245&cmid=3678 2/4 7/17/24, 12:47 AM Introduction to Generative Models - Pre Quiz: Attempt review Question 6 Correct Mark 1.00 out of 1.00 In the context of models, what does P(x | y) typically represent? The generative capacity of x The probability of x given y The likelihood of y The probability of y given x The distribution of y The correct answer is: The probability of x given y Question 7 Correct Mark 1.00 out of 1.00 57125 In the context of generative models, what does P(x) represent? The joint probability of x and y The probability distribution of the data x The conditional probability of x given y The likelihood of x The posterior probability of x 57125 The correct answer is: The probability distribution of the data x Question 8 Correct Mark 1.00 out of 1.00 Which statement best differentiates generative from discriminative models? Generative models are newer than discriminative models Both models serve the same purpose 57125 Generative models learn the joint probability distribution, while discriminative models learn the conditional probability Generative models cannot be trained with labeled data Generative models are only for images, discriminative for text The correct answer is: Generative models learn the joint probability distribution, while discriminative models learn the conditional probability https://accenturelearning.tekstac.com/mod/quiz/review.php?attempt=2948245&cmid=3678 3/4 7/17/24, 12:47 AM Introduction to Generative Models - Pre Quiz: Attempt review Question 9 Correct Mark 1.00 out of 1.00 If a model is better at distinguishing between classes rather than generating data, it is likely a _______. Bayesian model Joint probability model Discriminative model Likelihood model Generative model The correct answer is: Discriminative model Question 10 Correct Mark 1.00 out of 1.00 57125 What is the primary goal of generative models in AI? To classify data To analyze data distributions To reduce computational cost To optimize algorithms To generate new data samples 57125 The correct answer is: To generate new data samples ◄ Fundamentals of ML - Post Quiz Jump to... Introduction to Generative Models ► 57125 https://accenturelearning.tekstac.com/mod/quiz/review.php?attempt=2948245&cmid=3678 4/4 7/17/24, 1:03 AM Introduction to Generative Models - Post Quiz: Attempt review   Dashboard / Primer 2.0 - App Dev / Stage 1 / Gen AI / Introduction to Generative Models Quiz review Started on Wednesday, 17 July 2024, 12:55 AM State Finished Completed on Wednesday, 17 July 2024, 1:03 AM Time taken 8 mins 9 secs Marks 9.00/10.00 Grade 90.00 out of 100.00 Question 1 Correct Mark 1.00 out of 1.00 Which of the following best describes the difference between generative and discriminative models? 57125 Generative models are used for classification only Generative models are older in concept Generative models are always better Generative models learn the data distribution, while discriminative models learn the decision boundary Discriminative models can't generate data The correct answer is: Generative models learn the data distribution, while discriminative models learn the decision boundary Question 2 Correct Mark 1.00 out of 1.00 57125 For what tasks can generative models be applied? Data generation, denoising, inpainting, and more Classification only Only denoising Data labeling only Only data generation 57125 The correct answer is: Data generation, denoising, inpainting, and more https://accenturelearning.tekstac.com/mod/quiz/review.php?attempt=2948374&cmid=3679 1/4 7/17/24, 1:03 AM Introduction to Generative Models - Post Quiz: Attempt review Question 3 Correct Mark 1.00 out of 1.00 Within generative models, what function does the discriminator serve in GANs? To distinguish between real and generated data To generate new data To optimize the generator To calculate the likelihood To capture the joint probability The correct answer is: To distinguish between real and generated data Question 4 Correct Mark 1.00 out of 1.00 57125 What's a significant hurdle when training GANs? The discriminator becoming too weak Overfitting to the training data Inability to generate high-resolution images Mode collapse Slow convergence rate The correct answer is: Mode collapse 57125 Question 5 Correct Mark 1.00 out of 1.00 Which claim regarding generative models isn't true? They capture the data distribution They always require labeled data for training 57125 They can be used in unsupervised learning scenarios They can be combined with discriminative models for certain tasks They can generate new data samples The correct answer is: They always require labeled data for training https://accenturelearning.tekstac.com/mod/quiz/review.php?attempt=2948374&cmid=3679 2/4 7/17/24, 1:03 AM Introduction to Generative Models - Post Quiz: Attempt review Question 6 Incorrect Mark 0.00 out of 1.00 Which of the following is NOT a property of likelihood? It is always a probability between 0 and 1  It is not normalized like a probability It is a function of model parameters It measures how well a model explains data It can be used to compare different models The correct answer is: It is not normalized like a probability Question 7 Correct Mark 1.00 out of 1.00 57125 Which model type aims to capture the joint probability P(x, y)? Discriminative Model Both Generative Model and Discriminative Model Generative Model regression model Probability Distribution The correct answer is: Generative Model 57125 Question 8 Correct Mark 1.00 out of 1.00 What does a probability distribution provide? A decision boundary for classification A measure of model error 57125 A method for generating new data A training method for models A mathematical description of outcomes for a random variable The correct answer is: A mathematical description of outcomes for a random variable https://accenturelearning.tekstac.com/mod/quiz/review.php?attempt=2948374&cmid=3679 3/4 7/17/24, 1:03 AM Introduction to Generative Models - Post Quiz: Attempt review Question 9 Correct Mark 1.00 out of 1.00 How is the likelihood of data given a model symbolized? P(data) P(model) P(model | data) P(data | model) P(data & model) The correct answer is: P(data | model) Question 10 Correct Mark 1.00 out of 1.00 57125 Within the architecture of Generative Adversarial Networks (GANs), which duo of fundamental elements are paramount? Encoder and Decoder Classifier and Regressor Activator and Deactivator Forward and Backward Propagators Generator and Discriminator 57125 The correct answer is: Generator and Discriminator ◄ Introduction to Generative Models Jump to... Variational Autoencoders - Pre Quiz ► 57125 https://accenturelearning.tekstac.com/mod/quiz/review.php?attempt=2948374&cmid=3679 4/4 7/17/24, 10:26 AM Variational Autoencoders - Pre Quiz: Attempt review   Dashboard / Primer 2.0 - App Dev / Stage 1 / Gen AI / Variational Autoencoders Quiz review Started on Wednesday, 17 July 2024, 10:20 AM State Finished Completed on Wednesday, 17 July 2024, 10:26 AM Time taken 6 mins 12 secs Marks 10.00/10.00 Grade 100.00 out of 100.00 Question 1 Correct Mark 1.00 out of 1.00 In the context of Variational Autoencoders (VAEs), what does variational inference help achieve? Improved image resolution57125 Approximation of complex posterior distributions Faster training speeds Reduction of model parameters Direct computation of posterior distributions The correct answer is: Approximation of complex posterior distributions Question 2 Correct Mark 1.00 out of 1.00 57125 Which application does NOT typically use VAEs? Medical imaging enhancement Fashion design Text summarization Face generation for video games Anomaly detection in industrial equipment The correct answer is: Text summarization 57125 https://accenturelearning.tekstac.com/mod/quiz/review.php?attempt=2951447&cmid=3680 1/4 7/17/24, 10:26 AM Variational Autoencoders - Pre Quiz: Attempt review Question 3 Correct Mark 1.00 out of 1.00 Which of the following is NOT a type of autoencoder? Contractive autoencoder Supervised autoencoder Variational autoencoder Denoising autoencoder Sparse autoencoder The correct answer is: Supervised autoencoder Question 4 Correct Mark 1.00 out of 1.00 57125 Reparameterization trick is used to... None of the given options Reduce model size Deal with the non-differentiability of sampling in VAEs Speed up training Improve model accuracy 57125 The correct answer is: Deal with the non-differentiability of sampling in VAEs Question 5 Correct Mark 1.00 out of 1.00 What is the primary role of autoencoders in generative modeling? Regression Data compression and reconstruction 57125 Data classification Image recognition Clustering The correct answer is: Data compression and reconstruction https://accenturelearning.tekstac.com/mod/quiz/review.php?attempt=2951447&cmid=3680 2/4 7/17/24, 10:26 AM Variational Autoencoders - Pre Quiz: Attempt review Question 6 Correct Mark 1.00 out of 1.00 In which application might you use a VAE for generating new, coherent samples? Text translation Image classification Designing virtual fashion items Time series forecasting Speech recognition The correct answer is: Designing virtual fashion items Question 7 Correct Mark 1.00 out of 1.00 57125 Which component of the VAE loss function ensures the latent variables adhere to a standard distribution? Hinge loss Absolute error KL divergence Mean squared error Cross-entropy The correct answer is: KL divergence 57125 Question 8 Correct Mark 1.00 out of 1.00 Why are autoencoders considered generative models? They always reduce data dimensionality They are only used for image data 57125 They can reconstruct and generate data similar to the input They are used for supervised learning They are a type of neural network The correct answer is: They can reconstruct and generate data similar to the input https://accenturelearning.tekstac.com/mod/quiz/review.php?attempt=2951447&cmid=3680 3/4 7/17/24, 10:26 AM Variational Autoencoders - Pre Quiz: Attempt review Question 9 Correct Mark 1.00 out of 1.00 What does VAE stand for? Variable Autoencoder Virtual Autoencoder Vectorized Autoencoder None of the given options Variational Autoencoder The correct answer is: Variational Autoencoder Question 10 Correct Mark 1.00 out of 1.00 57125 Why is the reparameterization trick crucial in training VAEs? It speeds up the training process It reduces the model's complexity It reduces the need for labeled data It allows backpropagation through stochastic nodes It increases the model's accuracy 57125 The correct answer is: It allows backpropagation through stochastic nodes ◄ Introduction to Generative Models - Post Quiz Jump to... Variational Autoencoders ► 57125 https://accenturelearning.tekstac.com/mod/quiz/review.php?attempt=2951447&cmid=3680 4/4 7/17/24, 10:39 AM Variational Autoencoders - Post Quiz: Attempt review   Dashboard / Primer 2.0 - App Dev / Stage 1 / Gen AI / Variational Autoencoders Quiz review Started on Wednesday, 17 July 2024, 10:34 AM State Finished Completed on Wednesday, 17 July 2024, 10:39 AM Time taken 5 mins 7 secs Marks 10.00/10.00 Grade 100.00 out of 100.00 Question 1 Correct Mark 1.00 out of 1.00 Why is the reparameterization trick important in VAEs? 57125 It simplifies the model architecture It reduces overfitting It increases model efficiency It allows backpropagation through random nodes None of the given options The correct answer is: It allows backpropagation through random nodes Question 2 Correct Mark 1.00 out of 1.00 57125 Autoencoders primarily focus on which aspect of data? Generation Filtering Clustering Classification Reconstruction The correct answer is: Reconstruction 57125 https://accenturelearning.tekstac.com/mod/quiz/review.php?attempt=2951621&cmid=3681 1/4 7/17/24, 10:39 AM Variational Autoencoders - Post Quiz: Attempt review Question 3 Correct Mark 1.00 out of 1.00 Which of the following is a key component of the VAE loss function? Mean squared error only Accuracy KL divergence Cross-entropy only Precision The correct answer is: KL divergence Question 4 Correct Mark 1.00 out of 1.00 57125 Which of the following is NOT a typical use case for VAEs? Fashion design Real-time speech translation Medical imaging enhancement Face generation for video games Anomaly detection in industrial equipment 57125 The correct answer is: Real-time speech translation Question 5 Correct Mark 1.00 out of 1.00 In which application can VAEs detect unusual patterns? Anomaly detection in industrial equipment Music composition 57125 Text generation Face generation for video games Fashion design The correct answer is: Anomaly detection in industrial equipment https://accenturelearning.tekstac.com/mod/quiz/review.php?attempt=2951621&cmid=3681 2/4 7/17/24, 10:39 AM Variational Autoencoders - Post Quiz: Attempt review Question 6 Correct Mark 1.00 out of 1.00 What do VAEs use to generate a distribution over latent variables? Transfer learning Variational inference None of the given options Gradient descent Backpropagation The correct answer is: Variational inference Question 7 Correct Mark 1.00 out of 1.00 57125 Why is variational inference used in VAEs? To approximate intractable posterior distributions None of the given options To reduce model size To speed up training To improve model accuracy 57125 The correct answer is: To approximate intractable posterior distributions Question 8 Correct Mark 1.00 out of 1.00 In which application might VAEs be used to enhance image quality? None of the given options Medical imaging 57125 Video streaming Social media photo filters Text generation The correct answer is: Medical imaging https://accenturelearning.tekstac.com/mod/quiz/review.php?attempt=2951621&cmid=3681 3/4 7/17/24, 10:39 AM Variational Autoencoders - Post Quiz: Attempt review Question 9 Correct Mark 1.00 out of 1.00 Which optimization technique is commonly used with VAEs? Stochastic gradient descent (SGD) Genetic algorithms Principal component analysis Simulated annealing None of the given options The correct answer is: Stochastic gradient descent (SGD) Question 10 Correct Mark 1.00 out of 1.00 57125 How do VAEs differ from traditional autoencoders? VAEs are simpler VAEs are faster VAEs use supervised learning VAEs are more accurate VAEs introduce randomness via a probabilistic layer 57125 The correct answer is: VAEs introduce randomness via a probabilistic layer ◄ Variational Autoencoders Jump to... Case Study - Variational Auto Encoder ► 57125 https://accenturelearning.tekstac.com/mod/quiz/review.php?attempt=2951621&cmid=3681 4/4 7/17/24, 10:54 AM CASE STUDY - VAE Application - Quiz: Attempt review   Dashboard / Primer 2.0 - App Dev / Stage 1 / Gen AI / Variational Autoencoders Quiz review Started on Wednesday, 17 July 2024, 10:45 AM State Finished Completed on Wednesday, 17 July 2024, 10:54 AM Time taken 9 mins 9 secs Marks 12.00/15.00 Grade 80.00 out of 100.00 Question 1 Incorrect Mark 0.00 out of 1.00 Which is NOT a challenge in implementing VAEs for this use-case? Threshold Setting  Model Training 57125 Latency Data Quality Increasing data storage costs The correct answer is: Increasing data storage costs Question 2 Correct Mark 1.00 out of 1.00 57125 Why is understanding the VAE's outputs challenging? They are highly interpretable They are always correct They are too simplistic They use an unknown language They can be complex and non-intuitive 57125 The correct answer is: They can be complex and non-intuitive https://accenturelearning.tekstac.com/mod/quiz/review.php?attempt=2951807&cmid=7549 1/6 7/17/24, 10:54 AM CASE STUDY - VAE Application - Quiz: Attempt review Question 3 Incorrect Mark 0.00 out of 1.00 What is a primary application of VAEs mentioned in the case study? Text Summarization Anomaly Detection Image Classification  Speech Recognition Object Detection The correct answer is: Anomaly Detection Question 4 Incorrect Mark 0.00 out of 1.00 57125 How is the data divided for training the VAE? 60-40 90-10 50-50  70-30 80-20 The correct answer is: 80-20 57125 Question 5 Correct Mark 1.00 out of 1.00 What does the VAE attempt to minimize during training? Training time Latent space dimensions 57125 Data input size Loss Validation accuracy The correct answer is: Loss https://accenturelearning.tekstac.com/mod/quiz/review.php?attempt=2951807&cmid=7549 2/6 7/17/24, 10:54 AM CASE STUDY - VAE Application - Quiz: Attempt review Question 6 Correct Mark 1.00 out of 1.00 In the VAE, what does the sampling function introduce? Randomness Parallelism Linearity Recursion Determinism The correct answer is: Randomness Question 7 Correct Mark 1.00 out of 1.00 57125 What is the y-axis label of the chart visualizing the error? Data Value Timestamp Latent Space Anomaly Score Reconstruction Error The correct answer is: Reconstruction Error 57125 Question 8 Correct Mark 1.00 out of 1.00 For how many epochs is the VAE trained? 40 25 57125 10 50 100 The correct answer is: 50 https://accenturelearning.tekstac.com/mod/quiz/review.php?attempt=2951807&cmid=7549 3/6 7/17/24, 10:54 AM CASE STUDY - VAE Application - Quiz: Attempt review Question 9 Correct Mark 1.00 out of 1.00 What is the VAE trained to learn effectively? A textual description of the data A compressed representation of the data A visual representation of the data A highly detailed representation of the data A noisy representation of the data The correct answer is: A compressed representation of the data Question 10 Correct Mark 1.00 out of 1.00 57125 What criterion is used to determine if a data point is anomalous? If its error is above mean error If its error is above median error If its error is above the 99th percentile If its error is in the top 10% If its error is below mean error 57125 The correct answer is: If its error is above the 99th percentile Question 11 Correct Mark 1.00 out of 1.00 Over time, due to certain changes, what might be required of the VAE model? Manual recalibration Continuous adaptation 57125 Reformatting Disintegration Shrinking The correct answer is: Continuous adaptation https://accenturelearning.tekstac.com/mod/quiz/review.php?attempt=2951807&cmid=7549 4/6 7/17/24, 10:54 AM CASE STUDY - VAE Application - Quiz: Attempt review Question 12 Correct Mark 1.00 out of 1.00 Which of the following is NOT an attribute in the given data? Temperature Pressure Humidity Timestamp Vibration The correct answer is: Humidity Question 13 Correct Mark 1.00 out of 1.00 57125 What type of dataset does the manufacturing plant collect? Text Dataset Time Series Dataset Image Dataset Tabular Dataset Audio Dataset The correct answer is: Time Series Dataset 57125 Question 14 Correct Mark 1.00 out of 1.00 Why is data preprocessing required before training the VAE? To introduce errors into the data To make the data larger 57125 To make the data unreadable To make the data look visually appealing To ensure it is suitable for training The correct answer is: To ensure it is suitable for training https://accenturelearning.tekstac.com/mod/quiz/review.php?attempt=2951807&cmid=7549 5/6 7/17/24, 10:54 AM CASE STUDY - VAE Application - Quiz: Attempt review Question 15 Correct Mark 1.00 out of 1.00 What two components combine to form the VAE's loss? Classification error and Regression loss MSE and KL divergence KL divergence and Cross-entropy L1 loss and L2 loss MSE and Cross-entropy The correct answer is: MSE and KL divergence ◄ Case Study - Variational Auto Encoder Jump to... 57125 Generative Adversarial Networks - Pre Quiz ► 57125 57125 https://accenturelearning.tekstac.com/mod/quiz/review.php?attempt=2951807&cmid=7549 6/6 7/17/24, 8:32 PM Generative Adversarial Networks - Pre Quiz: Attempt review   Dashboard / Primer 2.0 - App Dev / Stage 1 / Gen AI / Generative Adversarial Networks Quiz review Started on Wednesday, 17 July 2024, 8:13 PM State Finished Completed on Wednesday, 17 July 2024, 8:32 PM Time taken 18 mins 53 secs Marks 10.00/10.00 Grade 100.00 out of 100.00 Question 1 Correct Mark 1.00 out of 1.00 What does GAN stand for? 57125 Generalized Artificial Network None of the given options Generative Analytical Network Gradient Augmented Network Generative Adversarial Network The correct answer is: Generative Adversarial Network Question 2 Correct Mark 1.00 out of 1.00 57125 Which type of GAN allows for generating data based on specific categories? Mode Collapse GAN Conditional GAN Progressive GAN Minimax GAN None of the given options The correct answer is: Conditional GAN 57125 https://accenturelearning.tekstac.com/mod/quiz/review.php?attempt=2962880&cmid=3682 1/4 7/17/24, 8:32 PM Generative Adversarial Networks - Pre Quiz: Attempt review Question 3 Correct Mark 1.00 out of 1.00 What is a challenge faced during GAN training due to the minimax game concept? Generator producing only a single mode Discriminator becoming too weak Quick convergence to a suboptimal solution Oscillations and non-convergence Overfitting to the training data The correct answer is: Oscillations and non-convergence Question 4 Correct Mark 1.00 out of 1.00 57125 In GANs, which component is responsible for evaluating the authenticity of data? None of the given options Generator Encoder Decoder Discriminator The correct answer is: Discriminator 57125 Question 5 Correct Mark 1.00 out of 1.00 Which of the following is a real-world application where GANs have shown significant promise? Image-to-image translation Speech recognition 57125 Image classification Time series forecasting Text summarization The correct answer is: Image-to-image translation https://accenturelearning.tekstac.com/mod/quiz/review.php?attempt=2962880&cmid=3682 2/4 7/17/24, 8:32 PM Generative Adversarial Networks - Pre Quiz: Attempt review Question 6 Correct Mark 1.00 out of 1.00 Which component of a GAN is responsible for generating new data samples? Encoder Generator Decoder Optimizer Discriminator The correct answer is: Generator Question 7 Correct Mark 1.00 out of 1.00 57125 In the GAN architecture, what is the primary goal of the Discriminator? Generate realistic data samples Ensure mode diversity Distinguish between real and generated samples Minimize the loss function Replicate the generator's output 57125 The correct answer is: Distinguish between real and generated samples Question 8 Correct Mark 1.00 out of 1.00 Progressive GANs are designed to address which challenge in traditional GANs? Slow training speeds Mode collapse 57125 Inability to generate colored images Training stability and generating high-resolution images Discriminator overpowering the generator The correct answer is: Training stability and generating high-resolution images https://accenturelearning.tekstac.com/mod/quiz/review.php?attempt=2962880&cmid=3682 3/4 7/17/24, 8:32 PM Generative Adversarial Networks - Pre Quiz: Attempt review Question 9 Correct Mark 1.00 out of 1.00 The training process of GANs is often likened to which game? Poker None of the given options Chess Sudoku Minimax The correct answer is: Minimax Question 10 Correct Mark 1.00 out of 1.00 57125 What is mode collapse in the context of GANs? When the generator produces limited varieties of outputs When the model overfits When the model converges too quickly When the discriminator becomes too powerful When the model underfits 57125 The correct answer is: When the generator produces limited varieties of outputs ◄ CASE STUDY - VAE Application - Quiz Jump to... Generative Adversarial Networks ► 57125 https://accenturelearning.tekstac.com/mod/quiz/review.php?attempt=2962880&cmid=3682 4/4 7/17/24, 9:19 PM Generative Adversarial Networks - Post Quiz: Attempt review   Dashboard / Primer 2.0 - App Dev / Stage 1 / Gen AI / Generative Adversarial Networks Quiz review Started on Wednesday, 17 July 2024, 9:14 PM State Finished Completed on Wednesday, 17 July 2024, 9:19 PM Time taken 4 mins 32 secs Marks 10.00/10.00 Grade 100.00 out of 100.00 Question 1 Correct Mark 1.00 out of 1.00 Mode collapse is problematic because... 57125 It makes the discriminator weak It speeds up training None of the given options It limits the diversity of generated outputs It requires more data The correct answer is: It limits the diversity of generated outputs Question 2 Correct Mark 1.00 out of 1.00 57125 Which GAN variant focuses on gradually increasing the resolution of generated images? Progressive GAN Mode Collapse GAN Minimax GAN None of the given options Conditional GAN The correct answer is: Progressive GAN 57125 https://accenturelearning.tekstac.com/mod/quiz/review.php?attempt=2964334&cmid=3683 1/4 7/17/24, 9:19 PM Generative Adversarial Networks - Post Quiz: Attempt review Question 3 Correct Mark 1.00 out of 1.00 What is a challenge in evaluating the performance of GANs? They always outperform other models None of the given options Determining the quality of generated data They are too fast They require large datasets The correct answer is: Determining the quality of generated data Question 4 Correct Mark 1.00 out of 1.00 57125 Which is NOT a real-world application of GANs? Style transfer Super-resolution imaging Art generation Data augmentation Real-time weather prediction 57125 The correct answer is: Real-time weather prediction Question 5 Correct Mark 1.00 out of 1.00 Which component of a GAN tries to produce fake data? Encoder None of the given options 57125 Discriminator Decoder Generator The correct answer is: Generator https://accenturelearning.tekstac.com/mod/quiz/review.php?attempt=2964334&cmid=3683 2/4 7/17/24, 9:19 PM Generative Adversarial Networks - Post Quiz: Attempt review Question 6 Correct Mark 1.00 out of 1.00 In the minimax game of GANs, what is the discriminator's goal? Minimize its own loss None of the given options Generate realistic data Distinguish between real and fake data Maximize the generator's loss The correct answer is: Distinguish between real and fake data Question 7 Correct Mark 1.00 out of 1.00 57125 Which GAN variant can be conditioned on labels to generate specific outputs? Progressive GAN Mode Collapse GAN Conditional GAN Minimax GAN None of the given options The correct answer is: Conditional GAN 57125 Question 8 Correct Mark 1.00 out of 1.00 In GANs, if the discriminator becomes too powerful, what can happen? The generator becomes powerful too The generator may struggle to improve 57125 The training process speeds up The model achieves perfect accuracy None of the given options The correct answer is: The generator may struggle to improve https://accenturelearning.tekstac.com/mod/quiz/review.php?attempt=2964334&cmid=3683 3/4 7/17/24, 9:19 PM Generative Adversarial Networks - Post Quiz: Attempt review Question 9 Correct Mark 1.00 out of 1.00 Which statement about GANs is true? They only work with images None of the given options They are a type of supervised learning They always converge to a solution They can generate new, previously unseen data The correct answer is: They can generate new, previously unseen data Question 10 Correct Mark 1.00 out of 1.00 57125 The generator's objective in GANs is to... Reduce mode collapse Classify real vs. fake Fool the discriminator None of the given options Improve model accuracy The correct answer is: Fool the discriminator 57125 ◄ Generative Adversarial Networks Jump to... Case Study - GAN - CIFAR ► 57125 https://accenturelearning.tekstac.com/mod/quiz/review.php?attempt=2964334&cmid=3683 4/4 7/17/24, 9:28 PM CASE STUDY - GANS - CIFAR - Quiz: Attempt review   Dashboard / Primer 2.0 - App Dev / Stage 1 / Gen AI / Generative Adversarial Networks Quiz review Started on Wednesday, 17 July 2024, 9:20 PM State Finished Completed on Wednesday, 17 July 2024, 9:28 PM Time taken 8 mins 25 secs Marks 12.00/15.00 Grade 80.00 out of 100.00 Question 1 Correct Mark 1.00 out of 1.00 Which activation function is used in the final layer of the generator model? softmax sigmoid 57125 tanh leakyrelu relu The correct answer is: tanh Question 2 Correct Mark 1.00 out of 1.00 57125 Which of the following best describes the role of the generator in a GAN? To evaluate the loss None of the given options To produce images To combine images To critique images The correct answer is: To produce images 57125 https://accenturelearning.tekstac.com/mod/quiz/review.php?attempt=2964458&cmid=7551 1/6 7/17/24, 9:28 PM CASE STUDY - GANS - CIFAR - Quiz: Attempt review Question 3 Correct Mark 1.00 out of 1.00 In the discriminator's code, which layer helps in reducing the dimensions of the input image? BatchNormalization UpSampling2D Reshape Conv2D with strides Dense The correct answer is: Conv2D with strides Question 4 Correct Mark 1.00 out of 1.00 57125 What are the two main components of a GAN? Generator & Evaluator Discriminator & Sampler Discriminator & Evaluator Generator & UpSampler Generator & Discriminator 57125 The correct answer is: Generator & Discriminator Question 5 Correct Mark 1.00 out of 1.00 In the generator code, what is the purpose of the Reshape layer? To flatten the images To critique the images 57125 To reshape the dense layer into a 3D tensor for images To upsample the images To normalize the image values The correct answer is: To reshape the dense layer into a 3D tensor for images https://accenturelearning.tekstac.com/mod/quiz/review.php?attempt=2964458&cmid=7551 2/6 7/17/24, 9:28 PM CASE STUDY - GANS - CIFAR - Quiz: Attempt review Question 6 Incorrect Mark 0.00 out of 1.00 Which of the following is NOT a feedback given to the generator during training? This is a genuine image  This is a fake image This image is pixelated This image looks like a car This image looks blurry The correct answer is: This image is pixelated Question 7 Correct Mark 1.00 out of 1.00 57125 During training, what does the generator use to improve itself? Feedback from the user Real images Feedback from both the user and the discriminator Feedback from the discriminator CIFAR-10 dataset 57125 The correct answer is: Feedback from the discriminator Question 8 Incorrect Mark 0.00 out of 1.00 Which technique can help in dealing with training instability in GANs? All of the given options  Noise addition 57125 Data augmentation Gradient clipping Dropout The correct answer is: Gradient clipping https://accenturelearning.tekstac.com/mod/quiz/review.php?attempt=2964458&cmid=7551 3/6 7/17/24, 9:28 PM CASE STUDY - GANS - CIFAR - Quiz: Attempt review Question 9 Incorrect Mark 0.00 out of 1.00 What is used to refine the models during training? Adam Optimizer All of the given options  Batch Normalization LeakyReLU Conv2D The correct answer is: Adam Optimizer Question 10 Correct Mark 1.00 out of 1.00 57125 What does the discriminator do in a GAN? Creates images Combines images Both create and evaluate images Enhances image resolution Evaluates if an image is real or fake 57125 The correct answer is: Evaluates if an image is real or fake Question 11 Correct Mark 1.00 out of 1.00 In the provided code, why is discriminator.trainable set to False when setting up the combined system? To speed up training To make sure only the generator is trained in this step 57125 None of the given options To prevent overfitting To increase discriminator's accuracy The correct answer is: To make sure only the generator is trained in this step https://accenturelearning.tekstac.com/mod/quiz/review.php?attempt=2964458&cmid=7551 4/6 7/17/24, 9:28 PM CASE STUDY - GANS - CIFAR - Quiz: Attempt review Question 12 Correct Mark 1.00 out of 1.00 How many images are there in each class of the CIFAR-10 dataset? 10000 5000 15000 12000 6000 The correct answer is: 6000 Question 13 Correct Mark 1.00 out of 1.00 57125 Which architecture can help address convergence issues in traditional GANs? RNN LSTM CNN DBN WGAN The correct answer is: WGAN 57125 Question 14 Correct Mark 1.00 out of 1.00 Why might someone want to use GANs on the CIFAR-10 dataset? To classify the images in the dataset To reduce the size of the dataset 57125 To critique the images in the dataset To delete images from the dataset To generate novel and relevant images to augment dataset The correct answer is: To generate novel and relevant images to augment dataset https://accenturelearning.tekstac.com/mod/quiz/review.php?attempt=2964458&cmid=7551 5/6 7/17/24, 9:28 PM CASE STUDY - GANS - CIFAR - Quiz: Attempt review Question 15 Correct Mark 1.00 out of 1.00 Which challenge refers to the generator producing limited varieties or even the same sample every time? All of the given options Mode Collapse Training Instability Data Augmentation Convergence Issues The correct answer is: Mode Collapse ◄ Case Study - GAN - CIFAR Jump to... 57125 Sequence Generation with RNNs - Pre Quiz ► 57125 57125 https://accenturelearning.tekstac.com/mod/quiz/review.php?attempt=2964458&cmid=7551 6/6 7/17/24, 9:34 PM Sequence Generation with RNNs - Pre Quiz: Attempt review   Dashboard / Primer 2.0 - App Dev / Stage 1 / Gen AI / Sequence Generation with RNNs Quiz review Started on Wednesday, 17 July 2024, 9:29 PM State Finished Completed on Wednesday, 17 July 2024, 9:33 PM Time taken 4 mins 39 secs Marks 9.00/10.00 Grade 90.00 out of 100.00 Question 1 Correct Mark 1.00 out of 1.00 In NLP, what does RNNs help to predict? Next image Next song note 57125 Next video frame None of the options given Next word The correct answer is: Next word Question 2 Correct Mark 1.00 out of 1.00 57125 In the context of natural language processing, how are RNNs typically utilized for machine translation? Encoding the input sequence and decoding the output sequence For clustering text data For image classification As a replacement for CNNs As discriminators in GANs 57125 The correct answer is: Encoding the input sequence and decoding the output sequence https://accenturelearning.tekstac.com/mod/quiz/review.php?attempt=2964673&cmid=3689 1/4 7/17/24, 9:34 PM Sequence Generation with RNNs - Pre Quiz: Attempt review Question 3 Correct Mark 1.00 out of 1.00 When using RNNs for music generation, what does each neuron in the output layer typically represent? A possible note or rest in the musical vocabulary A frequency band A time step in the generated sequence A note in the C major scale A specific instrument The correct answer is: A possible note or rest in the musical vocabulary Question 4 Correct Mark 1.00 out of 1.00 57125 Which of the following is NOT a type of RNN architecture? Simple RNN GRU Bidirectional RNN CNN LSTM The correct answer is: CNN 57125 Question 5 Correct Mark 1.00 out of 1.00 During the training of RNNs for sequence generation, what is the common technique used to mitigate the vanishing gradient problem? Gradient clipping L1 regularization 57125 Batch normalization Dropout Data augmentation The correct answer is: Gradient clipping https://accenturelearning.tekstac.com/mod/quiz/review.php?attempt=2964673&cmid=3689 2/4 7/17/24, 9:34 PM Sequence Generation with RNNs - Pre Q