Young Benjamin. Pragmatic Deep Learning for Dummies

2019. — 536 p.Artificial Intelligence (AI) especially Deep Learning (DL) has made tremendous progress in recent years. It start to spread in many areas, such as: image classification, voice recognition, text generation, language translation etc. As time goes by, it becomes apparent that deep learning will stay in the mainstream. As a technology people, it is time to keep updated with these new skill sets.
Well to really understand deep learning, a deep dive into the math is normally needed. Fortunately, tech world/knowledge are normally built on layers/blocks. Researchers/scientists has built a great deep learning foundation for us, we will standing on the shoulders of giants. In this book we will mainly focus on applications on top of them. From practical engineering point of view, we may not need a deep dive into a math in order to use it effectively. Just like we can write an awesome software running on CPU, we generally do not need to have a very deep understanding of CPU.
So in this books we are not trying to deep dive into the math, instead we are trying to get an intuition of neural network, understand deep learning deep enough so that we could use and apply it effectively in our daily job/use cases.
Quote from Andrew Ng, a famous AI researcher: "AI is the new electricity. About 100 years ago, electricity transformed every major industry. AI has advanced tothe point where it has the power to transform every major sector in coming years". 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. This book will help you learn and grasp deep learning technology from ground zero with many interesting real world examples. The books 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.What Is Deep Learning
Deep Neural Network Basic Concepts
Python and NumPy basic
Deep Learning Development Environments
MNIST CNN Example
Pre-trained model, transfer learning and fine-tuning
Recurrent neural network - how to handle sequences data
Natural Language Processing
Optical character recognition
Audio processing, speech processing
Autoencoder network
Deep reinforcement learning
Learning from scratch (self-play) AlphaZero
How to deploy deep learning model