Summary
Do you have difficulties to get started on pytorch even with online tutorials? Do you have trouble really understand PyTorch example code? Do you want to understand many state-of-art deep learning technologies with bare-minimum math?Do you have obstacles to implement a real-life deep learning projects in Pytorch?
Free lifetime upgrade ( for an electronic copy ) as the book has been and will be frequently updated according to readers' feedbacks. Previous buyers, please feel free to contact the author for free update ( electronic copy ).
This book series (vol1 and vol2) will ease these pains and help you learn and grasp latest pytorch deep learning technology from ground zero with many interesting real world examples. It could also be used as a quick guide on how to use and understand deep learning in the real life.
Description
Artificial Intelligence (AI), Machine Learning especially Deep Learning has made tremendous progress in recent years. It starts to spread to all industries.
Unless you are a refresh graduated student with AI/deep learning major, many of us do not have a formal machine learning/deep learning training before, so it is time to keep updated with latest technology.
Pytoch is a quite powerful, flexible and yet popular deep learning framework, but the learning curve could be steep if you do not have much deep learning background. This book will easy the pain and help you learn and grasp latest pytorch deep learning technology from ground zero with many interesting real world examples. It covers many state-of-art deep learning technologies, e.g. : Convoluational neural network (CNN), Recurrent neural network (RNN), Seq2Seq model, word emedding, Connectionist temporal calssification (CTC ), Attention, Transformer, BERT, Auto-encoder, Dynamic Memrory Network (DMN), Deep-Q-learning(DQN/DDQN), Monte Carlo Tree search (MCTS), Alphago/Alphazero etc. This book could also be used as a quick guide on how to use and understand deep learning in the real life.
Readers should have basic knowledge of python, scripting etc. Any constructive feedback is welcome.
Vol. 1 Table of Contents Introduction What is deep learning Deep neural network components, layers Deep learning development environments Python and Tensor basic Pytorch deep learning basic MNIST CNN example: A deep dive of how to handle image data Pre-trained model, transfer learning and fine-tuning Recurrent neural network - how to handle sequences data How to deploy deep learning model.

Vol.2: Table of Contents Natural Langauge Processing Optical character recognition Audio processing, speech processing Autoencoder network Deep reinforcement learning Learning from scratch (self-play) AlphaZero
Note:
a keras/tensorflow version of this book Deep Learning with Keras from Scratch could be bought at https://www.amazon.com/Learning-Keras-Scratch-Benjamin-Young/dp/1091838828