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

Géron, Aurélien

ISBN 10: 3960092121 / ISBN 13: 9783960092124

Published by Dpunkt.Verlag GmbH, 2023

About this Item

German language. 9.33x6.54x1.77 inches. In Stock.

Seller Inventory # __3960092121

Bibliographic Details

• Title: Praxiseinstieg Machine Learning mit Scikit-Learn, Keras und TensorFlow: Konzepte, Tools und Techniken für intelligente Systeme
• Publisher: Dpunkt.Verlag GmbH
• Publication Date: 2023
• Language: German
• ISBN 10: 3960092121
• ISBN 13: 9783960092124
• Binding: Paperback
• Condition: Brand New

About this title

Synopsis

Updated and expanded 3. Edition of the bestseller on TensorFlow and Deep Learning

• Now covers many new features from Scikit-Learn, as well as Hugging Face's Keras Tuner Library and Transformers NLP Library
• Methodically introduces you to the basics of machine learning with Scikit-Learn and conveys deep learning techniques with Keras and TensorFlow
• With numerous exercises and solutions.

Machine learning and deep learning in particular have experienced impressive breakthroughs in recent years. Meanwhile, even programmers who know little about this technology can implement machine learning programs with simple, efficient tools. This standard work uses concrete examples, a minimum of theory, and immediate Python frameworks (Scikit-Learn, Keras, and TensorFlow) to give you an intuitive understanding of the concepts and tools for developing intelligent systems.

In this updated 3rd Edition, Aurélien Géron covers a wide range of techniques: from simple linear regression to deep neural networks. Numerous code examples and exercises help you implement what you have learned in practice. All you need is some programming experience to start directly.

• Learn the basics of machine learning through an extensive sample project with Scikit-Learn
• Explore numerous models including Support Vector Machines, Decision Trees, Random Forests, and Ensemble Methods
• Use unsupervised learning such as dimension reduction, clustering and anomaly detection
• Create neural network architectures such as convolutional neural networks, recurrent neural networks, generative adversarial networks, autoencoders, diffusion models and transformers
• Use TensorFlow and Keras to create and train neural networks for computer vision, natural language processing, deep reinforcement learning, and generative models