
Автор: Mark Liu
Издательство: CRC Press
Год: 2024
Страниц: 465
Язык: английский
Формат: pdf (true)
Размер: 17.4 MB
The release of ChatGPT has kicked off an arms race in Machine Learning (ML), however ML has also been described as a black box and very hard to understand. Machine Learning, Animated eases you into basic ML concepts and summarizes the learning process in three words: initialize, adjust and repeat. This is illustrated step by step with animation to show how machines learn: from initial parameter values to adjusting each step, to the final converged parameters and predictions. This book teaches readers to create their own neural networks with dense and convolutional layers, and use them to make binary and multi-category classifications. Readers will learn how to build Deep Learning game strategies and combine this with reinforcement learning, witnessing AI achieve super-human performance in Atari games such as Breakout, Space Invaders, Seaquest and Beam Rider. The book provides an intuitive explanation of concepts such as Deep Learning, Q-learning, or the policy-gradient algorithm. You’ll learn how to implement these algorithms by following the examples and how to apply them to your own field, be that business, biology, medicine, or something else entirely. While most models are built by using the TensorFlow Keras API, you also learn to create ML models from scratch on your own, without resorting to any API. This book is divided into six parts. Part I discusses how to install Python and how to create animations with Python libraries.