Keras was created and is maintained by Francois Chollet. Keras lays claim to being designed for humans, so common use cases are simple to execute and the syntax is clear and comprehensible. Keras is made to work with a number of lower-level deep learning languages and, in this book, Keras will be the interface that we use to utilize a number of popular deep learning backends, including TensorFlow.
- Title Page
- Copyright and Credits
- Dedication
- About Packt
- Contributors
- Preface
- Section 1: Deep Learning Basics
- Machine Learning Basics
- Setting Up R for Deep Learning
- Artificial Neural Networks
- Section 2: Deep Learning Applications
- CNNs for Image Recognition
- Multilayer Perceptron for Signal Detection
- Neural Collaborative Filtering Using Embeddings
- Technical requirements
- Introducing recommender systems
- Collaborative filtering with neural networks
- Exploring embeddings
- Preparing, preprocessing, and exploring data
- Performing exploratory data analysis
- Creating user and item embeddings
- Building and training a neural recommender system
- Evaluating results and tuning hyperparameters
- Summary
- Deep Learning for Natural Language Processing
- Formatting data using tokenization
- Cleaning text to remove noise
- Applying word embeddings to increase usable data
- Clustering data into topic groups
- Summarizing documents using model results
- Creating an RBM
- Defining the Gibbs sampling rate
- Speeding up sampling with contrastive divergence
- Computing free energy for model evaluation
- Stacking RBMs to create a deep belief network
- Summary
- Long Short-Term Memory Networks for Stock Forecasting
- Generative Adversarial Networks for Faces
- Section 3: Reinforcement Learning
- Reinforcement Learning for Gaming
- Deep Q-Learning for Maze Solving
- Other Books You May Enjoy
Exploring Keras
-
No Comment
..................Content has been hidden....................
You can't read the all page of ebook, please click here login for view all page.