I started my career in neuroscience. I wanted to understand brains. That is still proving difficult, and somewhere along the way, I realized my real motivation was to build things, and I wound up working in AI. I love the elegance of mathematical models of the world. Even the simplest machine learning model has complex implications, and exploring them is a joy.
My knees tremble and my heart quakes when I think of how much work must have gone into these two companion volumes. Collectively, they are more than four times the length of my book, covering the whole of machine learning.
It is an essential encyclopedic resource that should be on the desk of anyone serious about machine learning.
A detailed and up-to-date introduction to machine learning, presented through the unifying lens of probabilistic modeling and Bayesian decision theory.
This book offers a detailed and up-to-date introduction to machine learning (including deep learning) through the unifying lens of probabilistic modeling and Bayesian decision theory. The book covers mathematical background (including linear algebra and optimization), basic supervised learning (including linear and logistic regression and deep neural networks), as well as more advanced topics (including transfer learning and unsupervised learning). End-of-chapter exercises allow students to apply what they have learned, and an appendix covers notation.
This is the practical book that best accompanies my book (which is more about the underlying ideas.)
If you want a book that will show you how deep learning systems are built in practice, then this is the best place to start. It’s full of code snippets that translate between theory and building real systems.
Deep learning has revolutionized pattern recognition, introducing tools that power a wide range of technologies in such diverse fields as computer vision, natural language processing, and automatic speech recognition. Applying deep learning requires you to simultaneously understand how to cast a problem, the basic mathematics of modeling, the algorithms for fitting your models to data, and the engineering techniques to implement it all. This book is a comprehensive resource that makes deep learning approachable, while still providing sufficient technical depth to enable engineers, scientists, and students to use deep learning in their own work. No previous background in machine learning…
The best parts of this book really represent a gold standard in pedagogical clarity.
Although it’s now twenty years old, there is still much to learn from this rather unconventional book that covers the boundary between machine learning, information theory, and Bayesian methods. There are also odd tangents and curiosities, some of which work better than others but are never dull.
Just writing this review makes me want to go back to it and squeeze more out of it.
Information theory and inference, taught together in this exciting textbook, lie at the heart of many important areas of modern technology - communication, signal processing, data mining, machine learning, pattern recognition, computational neuroscience, bioinformatics and cryptography. The book introduces theory in tandem with applications. Information theory is taught alongside practical communication systems such as arithmetic coding for data compression and sparse-graph codes for error-correction. Inference techniques, including message-passing algorithms, Monte Carlo methods and variational approximations, are developed alongside applications to clustering, convolutional codes, independent component analysis, and neural networks. Uniquely, the book covers state-of-the-art error-correcting codes, including low-density-parity-check codes, turbo…
This is a popular science book, so a little different from the others on this list. It is a beautifully written book that is accessible to people who don’t know much about AI but is simultaneously thought-provoking for experts.
It contains probably the best discussion of "intelligence" that I've read, interesting insights into how Google and other tech giants came to develop their machine learning strategy, and a fascinating chapter that views recommendation engines and their users as parts of a single intelligent organism. It's concise and easy to read.
I've read many popular AI books, which are highly variable in quality, and this criminally underappreciated work is the best by miles.
- The author is one of the most influential AI reseachers of recent decades.
- Written in an accessible language, the book provides a probing account of AI today and proposes a new narrative to connect and make sense of events that happened in the recent tumultuous past and enable us to think soberly about the road ahead.
- The book is divided into ten carefully crafted and easily-digestible chapters, each grapples with an important question for AI, ranging from the scientific concepts that underpin the technology to wider implications for society, using real examples wherever possible.
Of course, this is not the obvious book to recommend for reinforcement learning, but if you are a beginner, then it’s a quick and easy place to start. It’s compact and gets straight into the main algorithms.
It has a good balance between theory and code and will get you up and running quickly.
The Contemporary Introduction to Deep Reinforcement Learning that Combines Theory and Practice
Deep reinforcement learning (deep RL) combines deep learning and reinforcement learning, in which artificial agents learn to solve sequential decision-making problems. In the past decade deep RL has achieved remarkable results on a range of problems, from single and multiplayer games-such as Go, Atari games, and DotA 2-to robotics.
Foundations of Deep Reinforcement Learning is an introduction to deep RL that uniquely combines both theory and implementation. It starts with intuition, then carefully explains the theory of deep RL algorithms, discusses implementations in its companion software library SLM…
This book is about the ideas that underlie deep learning. The first part of the book introduces deep learning models and discusses how to train them, measure their performance, and improve this performance. The next part considers architectures that are specialized to images, text, and graph data.
If you know nothing about deep learning, this book will take you close to the frontier of research. If you are teaching deep learning, it has many novel illustrations, problems, and 68 Python notebooks for your class. If you work in or with deep learning, it will fill in the gaps in your knowledge and make you think about things you already know from different viewpoints.
This irreverent biography provides a rare window into the music industry from a promoter’s perspective. From a young age, Peter Jest was determined to make a career in live music, and despite naysayers and obstacles, he did just that, bringing national acts to his college campus atUW-Milwaukee, booking thousands of concerts across Wisconsin and the Midwest, and opening Shank Hall, the beloved Milwaukee venue named after a club in the cult film This Is Spinal Tap.
Jest established lasting friendships with John Prine, Arlo Guthrie, and others, but ultimately, this book tells a universal story of love and hope…
We Had Fun and Nobody Died: Adventures of a Milwaukee Music Promoter
The entertaining and inspiring story of a stubbornly independent promoter and club owner
This irreverent biography provides a rare window into the music industry from a promoter’s perspective. From a young age, Peter Jest was determined to make a career in live music, and despite naysayers and obstacles, he did just that, bringing national acts to his college campus at UW–Milwaukee, booking thousands of concerts across Wisconsin and the Midwest, and opening Shank Hall, the beloved Milwaukee venue named after a club in the cult film This Is Spinal Tap.
This funny, nostalgia-inducing book details the lasting friendships Jest established…
