Praxiseinstieg Machine Learning mit Scikit-Learn und TensorFlow: Konzepte, Tools und Techniken für intelligente Systeme (Animals)

Géron, Aurélien

ISBN 10: 3960090617 / ISBN 13: 9783960090618

Published by Dpunkt.Verlag GmbH, 2017

About this Item

Befriedigend/Good: Durchschnittlich erhaltenes Buch bzw. Schutzumschlag mit Gebrauchsspuren, aber vollständigen Seiten. / Describes the average WORN book or dust jacket that has all the pages present.

Seller Inventory # M03960090617-G

Bibliographic Details

• Title: Praxiseinstieg Machine Learning mit Scikit-Learn und TensorFlow: Konzepte, Tools und Techniken für intelligente Systeme (Animals)
• Publisher: Dpunkt.Verlag GmbH
• Publication Date: 2017
• Language: German
• ISBN 10: 3960090617
• ISBN 13: 9783960090618
• Binding: Soft cover
• Condition: good

About this title

Synopsis

Breakthroughs in deep learning have impressively advanced machine learning in recent years. Meanwhile, even programmers who know little about this technology can implement machine learning programs with simple, efficient tools. This practice-oriented book will show you how.

With concrete examples, a minimum of theory, and two immediately applicable Python frameworks - Scikit-Learn and TensorFlow - author Aurélien Géron helps you to gain an intuitive understanding of the concepts and tools for developing intelligent systems. You'll learn a variety of techniques, starting with simple linear regression to neural networks. Exercises on each chapter will help you put what you have learned into practice. All you need is some programming experience to start directly.

- Discover machine learning, especially neural networks and deep learning.
- Use scikit learning to trace a machine learning sample project from start to finish
- Explore various trainable models, including Support Vector Machines, Decision Trees, Random Forests, and Ensemble Methods
- Use the TensorFlow library to create and train neural networks
- Learn neural network architectures including convolutional networks, recurrent nets, and deep reinforcement learning
- Use techniques for training and scaling neural networks.
- Apply code examples without having to overwork machine learning theory or algorithms