Description
Book SynopsisThis book builds upon the foundations established in its first edition, with updated chapters and the latest code implementations to bring it up to date with Tensorflow 2.0.
Pro Deep Learning with TensorFlow 2.0 begins with the mathematical and core technical foundations of deep learning. Next, you will learn about convolutional neural networks, including new convolutional methods such as dilated convolution, depth-wise separable convolution, and their implementation. You''ll then gain an understanding of natural language processing in advanced network architectures such as transformers and various attention mechanisms relevant to natural language processing and neural networks in general. As you progress through the book, you''ll explore unsupervised learning frameworks that reflect the current state of deep learning methods, such as autoencoders and variational autoencoders. The final chapter covers the advanced topic of generative adversarial networks and their varia
Table of Contents
Chapter 1: Mathematical FoundationsChapter Goal: Setting the mathematical base for machine learning and deep learning .No of pages 100Sub -Topics1. Linear algebra 2. Calculus3. Probability4. Formulation of machine learning algorithms and optimization techniques.
Chapter 2: Introduction to Deep learning Concepts and Tensorflow 2.0 Chapter Goal: Setting the foundational base for deep learning and introduction to Tensorflow 2.0 programming paradigm. No of pages: 75Sub - Topics: 5. Deep learning and its evolution.6. Evolution of the learning techniques: from perceptron based learning to back-propagation7. Different deep learning objectives functions for supervised and unsupervised learning.8. Tensorflow 2.09. GPU
Chapter 3: Convolutional Neural networksChapter Goal: The mathematical and technical aspects of convolutional neural networkNo of pages: 801. Convolution operation2. Analog and digital signal3. 2D and 3D convolution, dilation and depth-wise separable convolution 4. Common image processing filter 5. Convolutional neural network and components6. Backpropagation through convolution and pooling layers7. Translational invariance and equivariance 8. Batch normalization9. Image segmentation and localization methods (Moved from advanced Neural Network to here, to make room for Graph Neural Networks )
Chapter 4: Deep learning for Natural Language Processing Chapter Goal: Deep learning methods and natural language processing No of pages:Sub - Topics: 1. Vector space model2. Word2Vec 3. Introduction to recurrent neural network and LSTM4. Attention 5. Transformer network architectures
Chapter 5: Unsupervised Deep Learning Methods
Chapter Goal: Foundations for different unsupervised deep learning techniques No of pages: 60Sub - Topics: 1. Boltzmann distribution2. Bayesian inference3. Restricted Boltzmann machines 4. Auto Encoders and variation methods
Chapter 6: Advanced Neural Networks Chapter Goal: Generative adversarial networks and graph neural networks No of pages: 70Sub - Topics: 1. Introduction to generative adversarial networks 2. CycleGAN, LSGAN Wasserstein GAN3. Introduction to graph neural network4. Graph attention network and graph SAGE
Chapter 7: Reinforcement Learning Chapter Goal: Reinforcement Learning using Deep Learning No of pages: 50Sub - Topics: 1. Introduction to reinforcement learning and MDP formulation2. Value based methods3. DQN4. Policy based methods5. Reinforce and actor critic network in policy based formulations6. Transition-less reinforcement learning and bandit methods
