Through a series of recent breakthroughs, deep learning has boosted the entire field of machine learning. Now, even programmers who know close to nothing about this technology can use simple, efficient tools to implement programs capable of learning from data. The updated edition of this best-selling book uses concrete examples, minimal theory, and production-ready Python frameworks to help you gain an intuitive understanding of the concepts and tools for building intelligent systems.
You’ll learn a range of techniques that you can quickly put to use. With exercises in each chapter to help you apply what you’ve learned, all you need is programming experience to get started. All code has been updated to TensorFlow 2 and the latest versions of Scikit-Learn and other libraries.
- Use Scikit-Learn to track an example machine learning project end-to-end
- Build and train neural nets using TensorFlow with the Keras API, then deploy them at scale across multiple cloud-based GPUs or on your own infrastructure
- Perform regression, classification, clustering, anomaly detection, object detection, semantic segmentation, image generation, and much more
- Explore models including support vector machines, decision trees, random forests, ensemble methods, and neural net architectures—including convolutional nets, recurrent nets, seq2seq encoder-decoders, transformers, autoencoders and GANs