E-book details

Deep Learning with Theano. Perform large-scale numerical and scientific computations efficiently

Deep Learning with Theano. Perform large-scale numerical and scientific computations efficiently

Christopher Bourez

Ebook
This book offers a complete overview of Deep Learning with Theano, a Python-based library that makes optimizing numerical expressions and deep learning models easy on CPU or GPU.

The book provides some practical code examples that help the beginner understand how easy it is to build complex neural networks, while more experimented data scientists will appreciate the reach of the book, addressing supervised and unsupervised learning, generative models, reinforcement learning in the fields of image recognition, natural language processing, or game strategy.

The book also discusses image recognition tasks that range from simple digit recognition, image classification, object localization, image segmentation, to image captioning. Natural language processing examples include text generation, chatbots, machine translation, and question answering. The last example deals with generating random data that looks real and solving games such as in the Open-AI gym.

At the end, this book sums up the best -performing nets for each task. While early research results were based on deep stacks of neural layers, in particular, convolutional layers, the book presents the principles that improved the efficiency of these architectures, in order to help the reader build new custom nets.

  • 1. Theano basics
  • 2. Classify handwritten digits with a feedforward network
  • 3. Encode word into vector
  • 4. Generate Text with a Recurrent Neural Net
  • 5. Analyze Sentiment with a Bidirectional LSTM
  • 6. Locate with Spatial Transformer Networks
  • 7. Classify Images with Residual Networks
  • 8. Translate and explain with encoding-decoding networks
  • 9. Select relevant inputs or memories with the mechanism of attention
  • 10. Predict Times Sequences with Advanced RNN
  • 11. Learning from the Environment with Reinforcement
  • 12. Learn Features with Unsupervised Generative Networks
  • 13. Extending Theano - What’s next?
  • Title: Deep Learning with Theano. Perform large-scale numerical and scientific computations efficiently
  • Author: Christopher Bourez
  • Original title: Deep Learning with Theano. Perform large-scale numerical and scientific computations efficiently
  • ISBN: 9781786463050, 9781786463050
  • Date of issue: 2017-07-31
  • Format: Ebook
  • Item ID: e_15nk
  • Publisher: Packt Publishing