Introduction to Artificial Intelligence
133 Questions
5 Views

Choose a study mode

Play Quiz
Study Flashcards
Spaced Repetition
Chat to lesson

Podcast

Play an AI-generated podcast conversation about this lesson

Questions and Answers

The size of our output layer depends on the number of __________________________ that we want our neural network to guess.

categories

How many output neurons will this network have?

  • 52 (correct)
  • 1,300 (correct)
  • 26 (correct)
  • 130 (correct)

    • What number does the program print for every epoch?

    loss value

    You want to see this number go __________ over time.

    <p>DOWN</p> Signup and view all the answers

    What is the tradeoff if you add more layers and neurons to your network to make it more accurate?

    <p>Increased computation time and risk of overfitting</p> Signup and view all the answers

    Where are the images for this step being stored?

    <p>In a directory or database</p> Signup and view all the answers

    Does the program process the story correctly?

    <p>YES</p> Signup and view all the answers

    What was added to the code?

    <p>Normalization techniques were applied, Each image was processed, Each image was resized to 28 x 28 pixels.</p> Signup and view all the answers

    Does the program work after the changes were made?

    <p>YES</p> Signup and view all the answers

    Which of the following use A.I.? (Circle all that apply)

    <p>YouTube</p> Signup and view all the answers

    How do you feel about A.I.?

    <p>Responses may vary</p> Signup and view all the answers

    Writers like to imagine a more _________________________ A.I.

    <p>generalized</p> Signup and view all the answers

    This is a realistic way to think of A.I.

    <p>False</p> Signup and view all the answers

    A machine is said to have artificial intelligence if it can _____________________________, potentially __________________ from the data, and use that knowledge to _____________ and achieve specific goals.

    <p>interpret data, learn, adapt</p> Signup and view all the answers

    Today's A.I. still can't do most of the things that humans do.

    <p>True</p> Signup and view all the answers

    A.I. is used to screen ____________________ applications.

    <p>college/job</p> Signup and view all the answers

    When was the term 'artificial intelligence' coined?

    <p>1956</p> Signup and view all the answers

    What important conference is responsible for a lot of advancements in A.I.?

    <p>Dartmouth Summer Research Project</p> Signup and view all the answers

    A.I. has developed SLOWER than these early thinkers predicted.

    <p>True</p> Signup and view all the answers

    When did the 'A.I. Winter' end?

    <p>Approximately 2010</p> Signup and view all the answers

    What 'two big developments' helped to spur the A.I. revolution forward?

    <p>Increase in computing power, Internet and Social Media</p> Signup and view all the answers

    What increases the speed of a computer?

    <p>More transistors</p> Signup and view all the answers

    When was the first iPhone released?

    <p>2007</p> Signup and view all the answers

    Scientists were inspired by the human brain when they made some kinds of A.I.

    <p>True</p> Signup and view all the answers

    What are the three basic parts of a neuron?

    <p>Dendrites, cell body, and axon</p> Signup and view all the answers

    What machine did Rosenblatt build and what was he trying to teach it to do?

    <p>The Perception; to classify shapes as triangles or not triangles.</p> Signup and view all the answers

    What special weight represents the threshold?

    <p>The Bias</p> Signup and view all the answers

    Generalized A.I. was successfully created in the early 2010’s.

    <p>False</p> Signup and view all the answers

    Name 2 different activation functions.

    <p>Logistic, Linear (any two from Logistic, Linear, Unit Step, Hyperbolic Tangent, Piecewise Linear, or Sign)</p> Signup and view all the answers

    At the beginning of supervised learning, the A.I. makes random guesses.

    <p>True</p> Signup and view all the answers

    When John Green Bot is correct, the update rule will add __ to the weight.

    <p>0</p> Signup and view all the answers

    John Green Bot learns from __.

    <p>FAILURE</p> Signup and view all the answers

    You can put the results of a supervised learning test into “a table, called a __.”

    <p>Confusion Matrix</p> Signup and view all the answers

    What is the key to most A.I. challenges?

    <p>Figuring out what criteria to use</p> Signup and view all the answers

    How many neurons does our brain have?

    <p>100 billion</p> Signup and view all the answers

    Who helped to develop A.I. that could recognize images?

    <p>Fei-Fei Li</p> Signup and view all the answers

    What was their international dataset called, and how many images does it have?

    <p>ImageNet; 3.2 million</p> Signup and view all the answers

    What made AlexNet different?

    <p>He used a lot of hidden layers and faster computation hardware.</p> Signup and view all the answers

    What layer mathematically combines the final hidden layer outputs?

    <p>Output layer</p> Signup and view all the answers

    What is the key to neural networks and all of A.I.?

    <p>Math</p> Signup and view all the answers

    Every hidden neuron looks for all of the components needed to determine if the picture is what they are looking for.

    <p>False</p> Signup and view all the answers

    How many neurons are in the output layer?

    <p>One</p> Signup and view all the answers

    Deeper neural networks are networks with more hidden layers to do deep learning.

    <p>True</p> Signup and view all the answers

    What is one way that neural networks are used in your life already?

    <p>Answers may vary</p> Signup and view all the answers

    Neural networks are now big enough that some can do tasks better than humans.

    <p>True</p> Signup and view all the answers

    What algorithm do neural networks use to handle mistakes?

    <p>Backpropagation</p> Signup and view all the answers

    What are the two main parts of neural networks?

    <p>The architecture and the weights</p> Signup and view all the answers

    The task of finding the best weights for a neural network architecture is called __.

    <p>Optimization</p> Signup and view all the answers

    What is the goal of linear regression?

    <p>To adjust the line to make the error as small as possible.</p> Signup and view all the answers

    What do neurons multiply the given features by?

    <p>The weights each has been assigned</p> Signup and view all the answers

    What represents the error when the predicted answer and the correct answer is more than just one number?

    <p>A Loss Function</p> Signup and view all the answers

    What algorithm did scientists create to help neural networks learn?

    <p>Backpropagation of the Error</p> Signup and view all the answers

    A local optimal solution is where the weights make the error relatively small, but not the smallest it could be.

    <p>True</p> Signup and view all the answers

    Ideally, you should explore different solutions at the same time, on the same neural network. However, that just isn’t feasible yet.

    <p>False</p> Signup and view all the answers

    Over time, backpropagation will adjust the neuron’s weights, so that the neural networks output matches the training data. That’s called __.

    <p>fitting to the training data</p> Signup and view all the answers

    What language will be used to write the code in this episode?

    <p>Python</p> Signup and view all the answers

    Where can you find the code that the episode is working on today?

    <p>There is a link to it in the video’s description.</p> Signup and view all the answers

    Step 1 includes training the network with 100,000 images.

    <p>False</p> Signup and view all the answers

    What dataset (abbreviated) will be used for this lab?

    <p>EMNIST</p> Signup and view all the answers

    What type of neural network will they be using in their episode?

    <p>Multi-layer perceptron neural network (MLP)</p> Signup and view all the answers

    How many output neurons will this network have?

    <p>26</p> Signup and view all the answers

    What number does the program print for every epoch?

    <p>Error of the Loss Function</p> Signup and view all the answers

    What is the tradeoff if you add more layers and neurons to your network to make it more accurate?

    <p>It will run slower</p> Signup and view all the answers

    Where are the images for this step being stored?

    <p>A GitHub Repository</p> Signup and view all the answers

    Does the program process the story correctly?

    <p>False</p> Signup and view all the answers

    What was added to the code?

    <p>Filters were applied; each image was centered; each image was resized to 28 x 28 pixels.</p> Signup and view all the answers

    Does the program work after the changes were made?

    <p>False</p> Signup and view all the answers

    Which of the following use A.I.? (Circle all that apply)

    <p>Doctors</p> Signup and view all the answers

    How do you feel about A.I.?

    <p>Response varies by person.</p> Signup and view all the answers

    Writers like to imagine a more ______ A.I.

    <p>advanced</p> Signup and view all the answers

    This is a realistic way to think of A.I.

    <p>True</p> Signup and view all the answers

    A machine is said to have artificial intelligence if it can ______, potentially ______ from the data, and use that knowledge to ______ and achieve specific goals.

    <p>learn, infer, act</p> Signup and view all the answers

    Today's A.I. still can't do most of the things that humans do.

    <p>True</p> Signup and view all the answers

    A.I. is used to screen ______ applications.

    <p>job</p> Signup and view all the answers

    When was the term 'artificial intelligence' coined?

    <p>1956</p> Signup and view all the answers

    What important conference is responsible for a lot of advancements in A.I.?

    <p>Dartmouth Conference</p> Signup and view all the answers

    A.I. has developed FASTER / SLOWER than these early thinkers predicted.

    <p>Faster</p> Signup and view all the answers

    When did the 'A.I. Winter' end?

    <p>Mid-1990s</p> Signup and view all the answers

    What 'two big developments' helped to spur the A.I. revolution forward? 1. Increase in ______ 2. ______ and ______.

    <p>computing power, data, algorithms</p> Signup and view all the answers

    What increases the speed of a computer?

    <p>More transistors</p> Signup and view all the answers

    When was the first iPhone released?

    <p>2007</p> Signup and view all the answers

    What process helps computers learn?

    <p>Machine learning</p> Signup and view all the answers

    What are the 'three main types of learning'?

    <p>Supervised, unsupervised, reinforced</p> Signup and view all the answers

    Supervised learning is the process of learning with ______.

    <p>labels</p> Signup and view all the answers

    What two things does an A.I. need to learn?

    <p>Data</p> Signup and view all the answers

    Scientists were inspired by the human brain when they made some kinds of A.I.

    <p>True</p> Signup and view all the answers

    What are the three basic parts of a neuron?

    <p>Dendrites, cell body, axon</p> Signup and view all the answers

    What machine did Rosenblatt build? What was he trying to teach it to do?

    <p>Perceptron, recognize images</p> Signup and view all the answers

    What special weight represents the threshold?

    <p>Bias weight</p> Signup and view all the answers

    Generalized A.I. was successfully created in the early 2010s.

    <p>False</p> Signup and view all the answers

    Name 2 different activation functions.

    <p>Sigmoid, ReLU</p> Signup and view all the answers

    At the beginning of supervised learning, the A.I. makes random guesses.

    <p>True</p> Signup and view all the answers

    When John Green Bot is correct, the update rule will add ______ to the weight.

    <p>value</p> Signup and view all the answers

    John Green Bot learns from ______.

    <p>success</p> Signup and view all the answers

    You can put the results of a supervised learning test into 'a table, called a ______.

    <p>confusion matrix</p> Signup and view all the answers

    ______ tells us how much you should ______ your program when it says it’s found something.

    <p>Precision, adjust</p> Signup and view all the answers

    ______ tells you how much your program can find of the thing you’re looking for.

    <p>Recall</p> Signup and view all the answers

    What is the 'key to most A.I. challenges?

    <p>Data quality and quantity</p> Signup and view all the answers

    How many neurons does our brain have?

    <p>100 billion</p> Signup and view all the answers

    Not that long ago, a big challenge in A.I. was ______ recognition.

    <p>image</p> Signup and view all the answers

    Who helped to develop A.I. that could recognize images?

    <p>Geoffrey Hinton</p> Signup and view all the answers

    What was their international dataset called? How many images does it have?

    <p>ImageNet, millions</p> Signup and view all the answers

    What made AlexNet different?

    <p>Used deep learning</p> Signup and view all the answers

    All neural networks are made up of an ______ layer, an ______ layer, and any number of ______ layers in between.

    <p>input, output, hidden</p> Signup and view all the answers

    Each pixel can be represented with 3 numbers that correspond to the amount of ______, ______, and ______ in the pixel.

    <p>red, green, blue</p> Signup and view all the answers

    What layer is 'where the final hidden layer outputs are mathematically combined to answer the problem?'

    <p>Output layer</p> Signup and view all the answers

    What is 'the key to neural networks and…all of A.I.'?

    <p>Backpropagation</p> Signup and view all the answers

    Every hidden neuron looks for all of the components needed to determine if the picture is what they are looking for.

    <p>True</p> Signup and view all the answers

    How many neurons are in the output layer?

    <p>Varies by use case</p> Signup and view all the answers

    Deeper neural networks 'are networks with more ______ to do deep ______.'

    <p>layers, learning</p> Signup and view all the answers

    What is one way that neural networks are used in your life already?

    <p>Facial recognition in photos</p> Signup and view all the answers

    Neural networks are now big enough that some can do tasks better than humans.

    <p>True</p> Signup and view all the answers

    What algorithm do neural networks use to handle mistakes?

    <p>Backpropagation</p> Signup and view all the answers

    What are the 'two main parts' of neural networks?

    <p>Nodes and connections</p> Signup and view all the answers

    The task of finding the best weights for a neural network architecture is called [blank].

    <p>Optimization</p> Signup and view all the answers

    What is 'the goal of linear regression?'

    <p>Predict outcomes</p> Signup and view all the answers

    By connecting together many simple ______ with ______, a neural network can learn to solve complicated ______.

    <p>neurons, weights, problems</p> Signup and view all the answers

    What do neurons multiply the given features by?

    <p>Weights</p> Signup and view all the answers

    What represents the error when 'the predicted answer and the correct answer is more than just one number?'

    <p>Loss function</p> Signup and view all the answers

    What algorithm did scientists create 'to help neural networks learn?'

    <p>Gradient descent</p> Signup and view all the answers

    A ______ is 'where the weights make the error relatively small, but not the smallest it could be.'

    <p>local minimum</p> Signup and view all the answers

    Ideally, you should explore different solutions at the same time, on the same neural network. However, that just isn’t feasible yet.

    <p>True</p> Signup and view all the answers

    ______ will adjust the neuron’s ______, so that the neural networks' output matches the ______.

    <p>Backpropagation, weights, target</p> Signup and view all the answers

    ______ is a very important step to training a good neural network.

    <p>Data preparation</p> Signup and view all the answers

    What language will be used to write the code in this episode?

    <p>Python</p> Signup and view all the answers

    Where can you find the code that the episode is working on today?

    <p>GitHub or related repository</p> Signup and view all the answers

    Our goal is to program a neural network to recognize ______ letters and convert them to ______.

    <p>handwritten, text</p> Signup and view all the answers

    Usually with a project like this, we’d have to write code to figure out where one letter ends and another begins...That’s called the ______.

    <p>segmentation algorithm</p> Signup and view all the answers

    Step 1: 'Find or create a ______ to train our neural network.'

    <p>dataset</p> Signup and view all the answers

    Step 2: 'Create a ______.'

    <p>model</p> Signup and view all the answers

    Step 3: 'Train, ______, and tweak our code until we feel that it’s ______ enough.'

    <p>test, accurate</p> Signup and view all the answers

    Step 1.2 includes training the network with 100,000 images.

    <p>True</p> Signup and view all the answers

    What dataset (abbreviated) will be used for this lab?

    <p>MNIST</p> Signup and view all the answers

    Study Notes

    What is Artificial Intelligence?

    • Artificial intelligence (AI) is used in many fields, including banking, healthcare, technology, and communication.
    • AI is often portrayed as a more advanced intelligence than humans, but this is a common misrepresentation.
    • AI is defined as a machine's ability to learn from data, and use that knowledge to make decisions and achieve goals.
    • AI often focuses on performing specific tasks, rather than mimicking human capabilities.
    • The term "artificial intelligence" was coined in 1956.
    • The Dartmouth Summer Research Project on Artificial Intelligence was a pivotal conference that significantly advanced the field.
    • The development of AI has been slower than early thinkers anticipated.
    • The field of AI experienced a "winter" period, where progress slowed down considerably before seeing a resurgence due to improvements in computing power and the availability of big data.

    Supervised Learning

    • AI systems learn through various processes, including supervised learning.
    • Supervised learning involves teaching the system with labeled data, providing the system with both input and corresponding output.
    • Supervised learning relies on having both data and an answer key.
    • The core component of machine learning is the neuron.
    • Neurons consist of dendrites, a cell body, and an axon.
    • One of the first AI projects was Rosenblatt's Perceptron, which aimed to teach a system to recognize patterns.
    • Activation functions, like the sigmoid and ReLU, determine a neuron's activation based on the weighted sum of its inputs.
    • Supervised learning uses a process of updating weights to improve accuracy, adjusting them based on success or failure.
    • Supervised learning results are organized in a confusion matrix, which helps evaluate performance.
    • Precision and recall are important metrics for evaluating the performance of supervised learning models.
    • The availability and quality of data are essential for training effective AI systems.

    What is Artificial Intelligence?

    • A.I. is used in many areas, such as banks, YouTube, and apps for cell phones
    • A machine is said to have artificial intelligence if it can interpret data, potentially learn from the data, and use that knowledge to adapt and achieve specific goals.
    • The term “artificial intelligence” was coined in 1956.
    • The Dartmouth Summer Research Project was responsible for many advancements in A.I.
    • The “A.I. Winter” ended around 2010.
    • The A.I. revolution was spurred on by the increase in computing power and the rise of the internet and social media.
    • More transistors increase the speed of a computer.
    • The first iPhone was released in 2007.

    Supervised Learning

    • Supervised learning is a way for computers to learn. Other types of learning include unsupervised and reinforcement learning.
    • Supervised learning is the process of learning with training labels.
    • An A.I. needs computing power and data to learn.
    • Scientists used the structure of neurons in the human brain to create certain types of A.I.
    • Neuron parts include dendrites, a cell body, and an axon.
    • The Perception was a machine built by Rosenblatt and designed to classify shapes as triangles or not triangles.
    • Bias is a special weight representing the threshold.
    • At the beginning of supervised learning, the A.I. makes random guesses.
    • John Green Bot is a system that learns by receiving updates based on its performance.
    • When John Green Bot is correct, the update rule assigns a weight of 0.
    • John Green Bot learns from its failures.
    • Supervised learning test results can be recorded in a Confusion Matrix.
    • Precision indicates the trustworthiness of an artificial intelligence system's output.
    • Recall measures the percentage of correct results.
    • The key to many A.I. challenges is "figuring out what criteria to use".

    Neural Networks and Deep Learning

    • Our brain has approximately 100 billion neurons.
    • Image recognition was a major challenge for A.I.
    • Fei-Fei Li contributed to the development of A.I. capable of image recognition.
    • ImageNet is a dataset of 3.2 million images.
    • AlexNet is a specific neural network that used many hidden layers and faster hardware.
    • Every neural network has an input layer, an output layer, and any number of hidden layers.
    • Each pixel can be represented by three numbers: red, green, and blue.
    • The output layer is where the final hidden layer outputs are combined to solve the problem.
    • Math is the key to neural networks and AI.
    • Deeper neural networks have more hidden layers to perform deep learning.

    Training Neural Networks

    • Neural networks are approaching or exceeding human capabilities in certain tasks.
    • Backpropagation is an algorithm commonly used for training neural networks to handle errors.
    • The two main components of neural networks are learning and adjusting the weights.
    • Backpropagation is the process of finding the optimal weights for a neural network architecture.
    • Linear regression seeks to identify a linear relationship between input and output parameters.
    • Complex problems can be solved by connecting simple neurons using weights.
    • Neurons multiply given features by specific weights.
    • The error, in cases where the predicted and correct answers differ by more than one number, is represented by the “loss” of the neural network.
    • Backpropagation is an algorithm designed to optimize the learning process of neural networks.
    • When the weights result in a relatively small but not minimal error, it's called a "local minimum."
    • Backpropagation fine-tunes the neuron’s weights to achieve a desired output, aligning with the training data. This process is called “gradient descent.”

    Neural Networks

    • Neural networks utilize backpropagation to handle mistakes.
    • Two main parts of neural networks: architecture and weights.
    • The process of finding the best weights for a neural network architecture is called optimization.
    • The goal of linear regression is to adjust the line to minimize error.
    • Neurons multiply given features by their assigned weights.
    • A Loss Function represents the error when the predicted answer and the correct answer differ by more than one number.
    • Backpropagation of the Error is an algorithm created to help neural networks learn.
    • A local optimal solution is where the weights minimize error, but not to the smallest possible value.
    • Backpropagation adjusts neuron weights over time to match the output to training data, a process called fitting to the training data.

    Crash Course Artificial Intelligence: How to Make an AI Read Handwriting (LAB)

    • The episode focuses on programming a neural network to recognize handwritten letters and convert them to typed text.
    • The code for the episode is written in Python and can be found in the video's description.
    • The process involves segmentation, which is figuring out where one letter ends and another begins.
    • The lab uses the EMNIST dataset.
    • The episode uses a multi-layer perceptron neural network (MLP).
    • The size of the output layer depends on the number of label types the network needs to guess.
    • The network has 26 output neurons, representing the letters of the alphabet.
    • During every epoch, the program prints the Error of the Loss Function, which should decrease over time.
    • Adding more layers and neurons to a network for accuracy leads to slower performance.
    • Images for the lab are stored in a GitHub repository.
    • The initial attempt at handwriting recognition fails.
    • The code is improved by applying filters, centering images, and resizing them to 28 x 28 pixels.
    • The improved code successfully recognizes most of the handwriting.

    Studying That Suits You

    Use AI to generate personalized quizzes and flashcards to suit your learning preferences.

    Quiz Team

    Related Documents

    Crash Course Artificial Intelligence Episodes #1-5 PDF

    Description

    This quiz covers the basics of Artificial Intelligence, exploring its definition, applications in various fields like banking and healthcare, and key historical milestones. Learn about the evolution of AI, including its challenges and breakthroughs over the years.

    More Like This

    Use Quizgecko on...
    Browser
    Open
    Browser
    Browser