Book Image

Deep Learning Essentials

By : Wei Di, Jianing Wei, Anurag Bhardwaj
3 (1)
Book Image

Deep Learning Essentials

3 (1)
By: Wei Di, Jianing Wei, Anurag Bhardwaj

Overview of this book

Deep Learning a trending topic in the field of Artificial Intelligence today and can be considered to be an advanced form of machine learning. This book will help you take your first steps in training efficient deep learning models and applying them in various practical scenarios. You will model, train, and deploy different kinds of neural networks such as CNN, RNN, and will see some of their applications in real-world domains including computer vision, natural language processing, speech recognition, and so on. You will build practical projects such as chatbots, implement reinforcement learning to build smart games, and develop expert systems for image captioning and processing using Python library such as TensorFlow. This book also covers solutions for different problems you might come across while training models, such as noisy datasets, and small datasets. By the end of this book, you will have a firm understanding of the basics of deep learning and neural network modeling, along with their practical applications.
Table of Contents (12 chapters)

Deep reinforcement learning

As explained in previous sections, there are few core components of any RL-based system. A value function v (s,θ) or a Q-function Q (s, a, θ), and a policy function π (a|s, θ), which could be model-free or model based. The wide scale applicability of any RL-based system depends on how good these estimations are. In practice, existing Q-learning systems suffer from multiple drawbacks:

  • Curse of dimensionality: If you were to apply a Q-learning-based technique to a high-dimensional RL setting, such as predicting the next joystick movement based on current pixel values of screen images of a game. A 32 x 32 sized image with boolean pixel values will lead to a total number of 21024 states. Q-learning will need a large number of samples to effectively deal with this state explosion.
  • Sample correlation: Given that a Q-learning update...