Deep Learning: Introduction - Lecture Slides

DEEP LEARNING Chapter 1: Introduction to Deep Learning Mr. Umesh Kumar, Lecturer, FICT All rights reserved. ©, ISBAT University,  Objective 2  To understand the concept of deep learning.  To understand supervised, u...

DEEP LEARNING Chapter 1: Introduction to Deep Learning Mr. Umesh Kumar, Lecturer, FICT All rights reserved. ©, ISBAT University,  Objective 2  To understand the concept of deep learning.  To understand supervised, unsupervised and reinforcement ML.  To understand the concept of Artificial Neural Network and their types.  To understand ML vs DL.  To understand Application and Challenges of Deep Learning. © ISBAT UNIVERSITY – 2024 04/23/25  Introduction 3  Deep learning is a branch of machine learning which is based on artificial neural networks.  An artificial neural network or ANN uses layers of interconnected nodes called neurons that work together to process and learn from the input data.  As it is based on artificial neural networks (ANNs) also known as deep neural networks (DNNs). These neural networks are inspired by the structure and function of the human brain’s biological neurons, and they are designed to learn from large amounts of data. © ISBAT UNIVERSITY – 2024. 04/23/25 4  The key characteristic of Deep Learning is the use of deep neural networks, which have multiple layers of interconnected nodes.  These networks can learn complex representations of data by discovering hierarchical patterns and features in the data.  Deep Learning algorithms can automatically learn and improve from data without the need for manual feature engineering. © ISBAT UNIVERSITY – 2024. 04/23/25 5  Deep Learning has achieved significant success in various fields, including image recognition, natural language processing, speech recognition, and recommendation systems.  Some of the popular Deep Learning architectures include:  Convolutional Neural Networks (CNNs)  Recurrent Neural Networks (RNNs)  Deep Belief Networks (DBNs)  Deep learning can be used for supervised, unsupervised as well as reinforcement machine learning. © ISBAT UNIVERSITY – 2024. 04/23/25  Supervised Machine Learning 6  Supervised machine learning is the machine learning technique in which the neural network learns to make predictions or classify data based on the labeled datasets.  Here we input both input features along with the target variables.  Deep learning algorithms like Convolutional neural networks, Recurrent neural networks are used for many supervised tasks like image classifications and recognization, sentiment analysis, language translations, etc. © ISBAT UNIVERSITY – 2024. 04/23/25  Unsupervised Machine Learning 7  Unsupervised machine learning is the machine learning technique in which the neural network learns to discover the patterns or to cluster the dataset based on unlabeled datasets.  Here there are no target variables. while the machine has to self-determined the hidden patterns or relationships within the datasets.  Deep learning algorithms like autoencoders and generative models are used for unsupervised tasks like clustering, dimensionality reduction, and anomaly detection. © ISBAT UNIVERSITY – 2024. 04/23/25  Reinforcement Machine Learning 8  Reinforcement Machine Learning is the machine learning technique in which an agent learns to make decisions in an environment to maximize a reward signal.  Deep reinforcement learning algorithms like Deep Q networks and Deep Deterministic Policy Gradient (DDPG) are used to reinforce tasks like robotics and game playing etc. © ISBAT UNIVERSITY – 2024. 04/23/25  Artificial Neural Networks 9  Artificial neural networks are built on the principles of the structure and operation of human neurons. It is also known as neural networks or neural nets.  An artificial neural network’s input layer, which is the first layer, receives input from external sources and passes it on to the hidden layer, which is the second layer.  Each neuron in the hidden layer gets information from the neurons in the previous layer, computes the weighted total, and then transfers it to the neurons in the next layer.  These connections are weighted, which means that the impacts of the inputs from the preceding layer are more or less optimized by giving each input a distinct weight.  These weights are then adjusted during the training process to enhance the performance of the model. © ISBAT UNIVERSITY – 2024. 04/23/25 10  The construct of a neural network consists of three components: neurons, layers, and weights.  Neuron - Basic units of the neural network containing individual data features.  Layers - A collection of unrelated neurons (the input layer) that connect to another set of neurons. This continues until the final layer of neurons (the output layer) is reached.  Weights affect the neuron connections between layers. © ISBAT UNIVERSITY – 2024. 04/23/25 11 © ISBAT UNIVERSITY – 2024. 04/23/25  Machine Learning VS Deep Learning 12 Machine Learning Deep Learning Apply statistical algorithms to learn the Uses artificial neural network architecture to hidden patterns and relationships in the learn the hidden patterns and relationships in dataset. the dataset. Can work on the smaller amount of dataset Requires the larger volume of dataset compared to machine learning Better for the low-label task. Better for complex task like image processing, natural language processing, etc. Takes less time to train the model. Takes more time to train the model. A model is created by relevant features Relevant features are automatically which are manually extracted from images to extracted from images. It is an end-to-end detect an object in the image. learning process. Less complex and easy to interpret the More complex, it works like the black box result. interpretations of the result are not easy. It can work on the CPU or requires less It requires a high-performance computer with computing power as compared to deep GPU. learning. © ISBAT UNIVERSITY – 2024. 04/23/25  Types of neural networks 13  Feedforward neural networks (FNNs) are the simplest type of ANN, with a linear flow of information through the network. FNNs have been widely used for tasks such as image classification, speech recognition, and natural language processing.  Convolutional Neural Networks (CNNs) are specifically for image and video recognition tasks. CNNs are able to automatically learn features from the images, which makes them well-suited for tasks such as image classification, object detection, and image segmentation.  Recurrent Neural Networks (RNNs) are a type of neural network that is able to process sequential data, such as time series and natural language. RNNs are able to maintain an internal state that captures information about the previous inputs, which makes them well-suited for tasks such as speech recognition, natural language processing, and language translation. © ISBAT UNIVERSITY – 2024. 04/23/25  Applications of Deep Learning 14  Computer Vision: Deep learning models can enable machines to identify and understand visual data. Some of the main applications of deep learning in computer vision include:  Object detection and recognition: Deep learning model can be used to identify and locate objects within images and videos, making it possible for machines to perform tasks such as self-driving cars, surveillance, and robotic.  Image classification: Deep learning models can be used to classify images into categories such as animals, plants, and buildings. This is used in applications such as medical imaging, quality control, and image retrieval.  Image segmentation: Deep learning models can be used for image segmentation into different regions, making it possible to identify specific features within images. © ISBAT UNIVERSITY – 2024. 04/23/25 15  Natural language processing (NLP):Deep learning model can enable machines to understand and generate human language. Some of the main applications of deep learning in NLP include:  Automatic Text Generation: Deep learning model can learn the corpus of text and new text like summaries, essays can be automatically generated using these trained models.  Language translation: Deep learning models can translate text from one language to another, making it possible to communicate with people from different linguistic backgrounds.  Sentiment analysis: Deep learning models can analyze the sentiment of a piece of text, making it possible to determine whether the text is positive, negative, or neutral. This is used in applications such as customer service, social media monitoring, and political analysis.  Speech recognition: Deep learning models can recognize and transcribe spoken words, making it possible to perform tasks such as speech-to-text conversion, voice search, and voice-controlled devices. © ISBAT UNIVERSITY – 2024. 04/23/25 16  Reinforcement learning: In reinforcement learning, deep learning works as training agents to take action in an environment to maximize a reward. Some of the main applications of deep learning in reinforcement learning include:  Game playing: Deep reinforcement learning models have been able to beat human experts at games such as Go, Chess, and Atari.  Robotics: Deep reinforcement learning models can be used to train robots to perform complex tasks such as grasping objects, navigation, and manipulation.  Control systems: Deep reinforcement learning models can be used to control complex systems such as power grids, traffic management, and supply chain optimization. © ISBAT UNIVERSITY – 2024. 04/23/25  Challenges in Deep Learning 17  Data availability: It requires large amounts of data to learn from. For using deep learning it’s a big concern to gather as much data for training.  Computational Resources: For training the deep learning model, it is computationally expensive because it requires specialized hardware like GPUs and TPUs.  Time-consuming: While working on sequential data depending on the computational resource it can take very large even in days or months.  Interpretability: Deep learning models are complex, it works like a black box. it is very difficult to interpret the result.  Overfitting: when the model is trained again and again, it becomes too specialized for the training data, leading to overfitting and poor performance on new data. © ISBAT UNIVERSITY – 2024. 04/23/25 18 Thank you © ISBAT UNIVERSITY – 2024. 04/23/25