Deep Learning with Keras by Antonio Gulli,Sujit Pal PDF

Key Features

• Implement quite a few deep-learning algorithms in Keras and notice how deep-learning can be utilized in games
• See how numerous deep-learning versions and sensible use-cases might be carried out utilizing Keras
• A sensible, hands-on consultant with real-world examples to offer you a powerful beginning in Keras

Book Description

This e-book begins by way of introducing you to supervised studying algorithms comparable to basic linear regression, the classical multilayer perceptron and extra subtle deep convolutional networks. additionally, you will discover photograph processing with popularity of hand written digit pictures, category of pictures into diversified different types, and complicated items popularity with comparable snapshot annotations. An instance of identity of salient issues for face detection is additionally supplied. subsequent you'll be brought to Recurrent Networks, that are optimized for processing series information similar to textual content, audio or time sequence. Following that, you are going to find out about unsupervised studying algorithms resembling Autoencoders and the very hot Generative adverse Networks (GAN). additionally, you will discover non-traditional makes use of of neural networks as type Transfer.

Finally, you are going to examine Reinforcement studying and its software to AI video game taking part in, one other renowned path of study and alertness of neural networks.

What you are going to learn

• Optimize step by step features on a wide neural community utilizing the Backpropagation Algorithm
• Fine-tune a neural community to enhance the standard of results
• Use deep studying for photo and audio processing
• Use Recursive Neural Tensor Networks (RNTNs) to outperform average notice embedding in particular cases
• Identify difficulties for which Recurrent Neural community (RNN) recommendations are suitable
• Explore the method required to enforce Autoencoders
• Evolve a deep neural community utilizing reinforcement learning

About the Author

Antonio Gulli is a software program govt and enterprise chief with a keenness for developing and handling international technological expertise, innovation, and execution. he's knowledgeable in se's, on-line providers, desktop studying, info retrieval, analytics, and cloud computing. to this point, he has been fortunate sufficient to realize specialist adventure in 4 varied nations in Europe and controlled humans in six various international locations in Europe and the USA. Antonio served as CEO, GM, CTO, vice chairman, director, and location lead in a number of fields spanning from publishing (Elsevier) to buyer web (Ask.com and Tiscali) and high-tech R&D (Microsoft and Google).

Sujit Pal is a know-how study director at Elsevier Labs, engaged on construction clever platforms round examine content material and metadata. His basic pursuits are info retrieval, ontologies, typical language processing, computing device studying, and disbursed processing. he's at the moment engaged on picture type and similarity utilizing deep studying versions. ahead of this, he labored within the customer healthcare undefined, the place he helped construct ontology-backed semantic seek, contextual advertisements, and EMR info processing systems. He writes approximately expertise on his web publication at Salmon Run.

Table of Contents

1. Neural Networks Foundations
2. Keras set up and API
3. Deep studying with ConvNets
4. Generative hostile Networks and WaveNet
5. Word Embeddings
6. Recurrent Neural community — RNN
7. Additional Deep studying Models
8. AI video game Playing
9. Conclusion