Here's 4 amazing resources to learn AI and ML:
Artificial Intelligence: A Modern Approach, 4th edition (aima.cs.berkeley.edu)
paid • book • by Stuart Russell, Peter Norvig • 2020
The authoritative, most-used AI textbook adopted by over 1500 schools. It explores the full breadth of AI, which encompasses logic and probability; perception, reasoning, learning, and action; fairness, trust, social good, and safety; and applications that range from microelectronic devices to robotic planetary explorers to online services with billions of users.
Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow, 3rd edition (www.oreilly.com)
paid • book • by Aurélien Géron • 2022
This book is a comprehensive, practical introduction to machine learning with Python. It covers classical ML algorithms including linear regression and classification, SVMs, decision trees, ensembles of models, PCA, and unsupervised learning algorithms. It also covers neural networks, reinforcement learning, and popular deep learning architectures such as CNNs, RNNs, transformers, autoencoders, diffusion models, and GANs. This book is an excellent way to get basic theoretical knowledge and hands-on experience in all major topics of machine learning.
Deep Learning with Python, 2nd edition (www.manning.com)
paid • book • by François Chollet • 2021
This book is a guide on how to build and train neural networks with Keras and TensorFlow by the author of Keras. You'll get hands-on experience in solving all kinds of ML problems including tabular data classification and regression, text classification, image classification, timeseries forecasting, machine translation, text generation, and image generation. And you'll learn about the fundamental and state-of-the-art deep learning methods to solve those problems: densely connected networks, CNNs, RNNs, transformers, autoencoders, and GANs. This book offers a unique blend of practical advice, deep learning theory, and insights into the nature of intelligence and cognition.
Awesome Production Machine Learning (github.com)
free • resource • by EthicalML • 2023
A curated list of open source libraries and platforms to deploy, monitor, version and scale your machine learning.