On Deep Learning

Abstract

2nd ed. Description based upon print version of record. Types of GANs The book will help you learn deep neural networks and their applications in computer vision, generative models, and natural language processing. It will also introduce you to the area of reinforcement learning, where you'll learn the state-of-the-art algorithms to teach the machines how to play games like Go and Atari. Cover; Title Page; Copyright and Credits; About Packt; Contributors; Table of Contents; Preface; Chapter 1: Machine Learning -- an Introduction; Introduction to machine learning; Different machine learning approaches; Supervised learning; Linear and logistic regression; Support vector machines; Decision Trees; Naive Bayes; Unsupervised learning; K-means; Reinforcement learning; Q-learning; Components of an ML solution; Neural networks; Introduction to PyTorch; Summary; Chapter 2: Neural Networks; The need for neural networks; An introduction to neural networks; An introduction to neurons An introduction to layersMulti-layer neural networks; Different types of activation function; Putting it all together with an example; Training neural networks ; Linear regression; Logistic regression; Backpropagation; Code example of a neural network for the XOR function ; Summary; Chapter 3: Deep Learning Fundamentals; Introduction to deep learning; Fundamental deep learning concepts ; Feature learning; Deep learning algorithms; Deep networks; A brief history of contemporary deep learning; Training deep networks; Applications of deep learning; The reasons for deep learning's popularity Introducing popular open source librariesTensorFlow; Keras; PyTorch; Using Keras to classify handwritten digits; Using Keras to classify images of objects; Summary; Chapter 4: Computer Vision with Convolutional Networks; Intuition and justification for CNN; Convolutional layers; A coding example of convolution operation; Stride and padding in convolutional layers; 1D, 2D, and 3D convolutions; 1x1 convolutions; Backpropagation in convolutional layers; Convolutional layers in deep learning libraries; Pooling layers; The structure of a convolutional network Classifying handwritten digits with a convolutional network Improving the performance of CNNs; Data pre-processing; Regularization; Weight decay; Dropout; Data augmentation; Batch normalization; A CNN example with Keras and CIFAR-10; Summary; Chapter 5: Advanced Computer Vision; Transfer learning; Transfer learning example with PyTorch; Advanced network architectures; VGG; VGG with Keras, PyTorch, and TensorFlow; Residual networks; Inception networks; Inception v1; Inception v2 and v3; Inception v4 and Inception-ResNet; Xception and MobileNets; DenseNets; Capsule networks Limitations of convolutional networksCapsules; Dynamic routing; Structure of the capsule network; Advanced computer vision tasks; Object detection; Approaches to object detection; Object detection with YOLOv3; A code example of YOLOv3 with OpenCV; Semantic segmentation; Artistic style transfer; Summary; Chapter 6: Generating Images with GANs and VAEs; Intuition and justification of generative models; Variational autoencoders; Generating new MNIST digits with VAE; Generative Adversarial networks; Training GANs; Training the discriminator; Training the generator; Putting it all together