Download e-book for kindle: Deep Learning with Keras by Antonio Gulli,Sujit Pal

Key Features

• Implement quite a few deep-learning algorithms in Keras and spot how deep-learning can be utilized in games
• See how quite a few deep-learning types and useful use-cases will be carried out utilizing Keras
• A functional, hands-on consultant with real-world examples to offer you a robust starting place in Keras

Book Description

This e-book begins through introducing you to supervised studying algorithms similar to uncomplicated linear regression, the classical multilayer perceptron and extra refined deep convolutional networks. additionally, you will discover photograph processing with popularity of hand written digit photos, type of pictures into diverse different types, and complex gadgets attractiveness with similar photograph annotations. An instance of id of salient issues for face detection can be supplied. subsequent you can be brought to Recurrent Networks, that are optimized for processing series information akin to textual content, audio or time sequence. Following that, you are going to know about unsupervised studying algorithms reminiscent of Autoencoders and the very hot Generative antagonistic Networks (GAN). additionally, you will discover non-traditional makes use of of neural networks as sort Transfer.

Finally, you are going to examine Reinforcement studying and its software to AI online game taking part in, one other well known path of analysis and alertness of neural networks.

What you'll learn

• Optimize step by step services on a wide neural community utilizing the Backpropagation Algorithm
• Fine-tune a neural community to enhance the standard of results
• Use deep studying for photograph and audio processing
• Use Recursive Neural Tensor Networks (RNTNs) to outperform normal notice embedding in designated cases
• Identify difficulties for which Recurrent Neural community (RNN) strategies 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 company chief with a fondness for developing and dealing with international technological expertise, innovation, and execution. he's knowledgeable in se's, on-line prone, computer studying, details retrieval, analytics, and cloud computing. to date, he has been fortunate sufficient to achieve expert event in 4 various nations in Europe and controlled humans in six various nations in Europe and the United States. Antonio served as CEO, GM, CTO, vice chairman, director, and placement lead in a number of fields spanning from publishing (Elsevier) to client net (Ask.com and Tiscali) and high-tech R&D (Microsoft and Google).

Sujit Pal is a know-how learn director at Elsevier Labs, engaged on construction clever platforms round examine content material and metadata. His fundamental pursuits are details retrieval, ontologies, common language processing, computing device studying, and disbursed processing. he's at the moment engaged on snapshot category and similarity utilizing deep studying types. ahead of this, he labored within the buyer healthcare undefined, the place he helped construct ontology-backed semantic seek, contextual advertisements, and EMR information processing systems. He writes approximately know-how 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 opposed Networks and WaveNet
5. Word Embeddings
6. Recurrent Neural community — RNN
7. Additional Deep studying Models
8. AI video game Playing
9. Conclusion