Here are 67 books that Information Theory, Inference and Learning Algorithms fans have personally recommended if you like
Information Theory, Inference and Learning Algorithms.
Shepherd is a community of 12,000+ authors and super readers sharing their favorite books with the world.
My primary interest is in brain function. Because the principal job of
the brain is to process information, it is necessary to define exactly
what information is. For that, there is no substitute for Claude
Shannon’s theory of information. This theory is not only quite
remarkable in its own right, but it is essential for telecoms,
computers, machine learning (and understanding brain function).
I have written ten "tutorial introduction" books, on topics which vary
from quantum mechanics to AI.
In a parallel universe, I am still an Associate Professor at the
University of Sheffield, England.
Pierce was a contemporary of Claude Shannon (inventor of information theory), so he learned information theory shortly after it was published in 1949. Pierce writes in an informal style, but does not flinch from presenting the fundamental theorems of information theory. Some would say his style is too wordy, and the ratio of words/equations is certainly very high. Nevertheless, this book provides a solid introduction to information theory. It was originally published in 1961, so it is a little dated in terms of topics covered. However, because it was re-published by Dover in 1981, it is also fairly cheap. Overall, this is a sensible first book to read on information theory.
"Uncommonly good...the most satisfying discussion to be found." — Scientific American. Behind the familiar surfaces of the telephone, radio, and television lies a sophisticated and intriguing body of knowledge known as information theory. This is the theory that has permitted the rapid development of all sorts of communication, from color television to the clear transmission of photographs from the vicinity of Jupiter. Even more revolutionary progress is expected in the future. To give a solid introduction to this burgeoning field, J. R. Pierce has revised his well-received 1961 study of information theory for a second edition. Beginning with the origins…
My primary interest is in brain function. Because the principal job of
the brain is to process information, it is necessary to define exactly
what information is. For that, there is no substitute for Claude
Shannon’s theory of information. This theory is not only quite
remarkable in its own right, but it is essential for telecoms,
computers, machine learning (and understanding brain function).
I have written ten "tutorial introduction" books, on topics which vary
from quantum mechanics to AI.
In a parallel universe, I am still an Associate Professor at the
University of Sheffield, England.
This is the modern standard text on information theory. It is both comprehensive and highly technical. The layout is spacey, and the authors make good use of the occasional diagram to explain geometric aspects of information theory. One feature I really like is the set of historical notes and a summary of equations at the end of each chapter.
The latest edition of this classic is updated with new problem sets and material The Second Edition of this fundamental textbook maintains the book's tradition of clear, thought-provoking instruction. Readers are provided once again with an instructive mix of mathematics, physics, statistics, and information theory. All the essential topics in information theory are covered in detail, including entropy, data compression, channel capacity, rate distortion, network information theory, and hypothesis testing. The authors provide readers with a solid understanding of the underlying theory and applications. Problem sets and a telegraphic summary at the end of each chapter further assist readers. The…
I am a financial data scientist. I think it is important that data scientists are highly specialized if they want to be effective in their careers. I run a business called Conlan Scientific out of Charlotte, NC where me and my team of financial data scientists tackle complicated machine learning problems for our clients. Quant trading is a gladiator’s arena of financial data science. Anyone can try it, but few succeed at it. I am sharing my top five list of math books that are essential to success in this field. I hope you enjoy.
While studying computer networks, Claude Shannon did something pretty impressive. He reformulated the majority of classical statistics from scratch using the language and concepts of computer science.
Statistical noise? There’s a new word for that; it’s called entropy. Also, it turns out it is a good thing, not a bad thing because entropy is equal to the information content or a data set. Tired of minimizing the squared error of everything? That’s fine, minimize the log of its likelihood instead. It does the same thing. This book challenges the assumptions of classical statistics in a way that fits neatly in the mind of a computer scientist. As a quant trader, this book will help you understand and measure the information content of data, which is critical to your success.
Scientific knowledge grows at a phenomenal pace--but few books have had as lasting an impact or played as important a role in our modern world as The Mathematical Theory of Communication, published originally as a paper on communication theory more than fifty years ago. Republished in book form shortly thereafter, it has since gone through four hardcover and sixteen paperback printings. It is a revolutionary work, astounding in its foresight and contemporaneity. The University of Illinois Press is pleased and honored to issue this commemorative reprinting of a classic.
Tap Dancing on Everest, part coming-of-age memoir, part true-survival adventure story, is about a young medical student, the daughter of a Holocaust survivor raised in N.Y.C., who battles self-doubt to serve as the doctor—and only woman—on a remote Everest climb in Tibet.
My primary interest is in brain function. Because the principal job of
the brain is to process information, it is necessary to define exactly
what information is. For that, there is no substitute for Claude
Shannon’s theory of information. This theory is not only quite
remarkable in its own right, but it is essential for telecoms,
computers, machine learning (and understanding brain function).
I have written ten "tutorial introduction" books, on topics which vary
from quantum mechanics to AI.
In a parallel universe, I am still an Associate Professor at the
University of Sheffield, England.
This is a more comprehensive and mathematically rigorous book than Pierce’s book. For the novice, it should be read-only after first reading Pierce’s more informal text. Due to its vintage, the layout is fairly cramped, but the content is impeccable. At almost 500 pages, it covers a huge amount of material. This was my main reference book on information theory for many years, but it now sits alongside more recent texts, like MacKay’s book (see below). It is also published by Dover, so it is reasonably priced.
Written for an engineering audience, this book has a threefold purpose: (1) to present elements of modern probability theory — discrete, continuous, and stochastic; (2) to present elements of information theory with emphasis on its basic roots in probability theory; and (3) to present elements of coding theory. The emphasis throughout the book is on such basic concepts as sets, the probability measure associated with sets, sample space, random variables, information measure, and capacity. These concepts proceed from set theory to probability theory and then to information and coding theories. No formal prerequisites are required other than the usual undergraduate…
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.
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.
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…
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.
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.
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.
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…
My name is Daniel Robert McClure, and I am an Associate Professor of History at Fort Hays State University in Hays, Kansas. I teach U.S., African diaspora, and world history, and I specialize in cultural and economic history. I was originally drawn to “information” and “knowledge” because they form the ties between culture and economics, and I have been teaching history through “information” for about a decade. In 2024, I was finally able to teach a graduate course, “The Origins of the Knowledge Society,” out of which came the “5 books.”
This book starts in a similar historical location as Bod’s book but quickly moves through the nineteenth and twentieth centuries—settling into the “information theory” era established by Claude Shannon, Norbert Wiener, and others in the 1940s-1960s.
I love this book because it situates the intellectual climate leading to our current dystopia of information overload. Gleick’s teasing of chaos theory inevitably pushes the reader to explore his book on the subject from the 1980s: Chaos: Making a New Science (1987).
Winner of the Royal Society Winton Prize for Science Books 2012, the world's leading prize for popular science writing.
We live in the information age. But every era of history has had its own information revolution: the invention of writing, the composition of dictionaries, the creation of the charts that made navigation possible, the discovery of the electronic signal, the cracking of the genetic code.
In 'The Information' James Gleick tells the story of how human beings use, transmit and keep what they know. From African talking drums to Wikipedia, from Morse code to the 'bit', it is a fascinating…
After World imagines a not-so-distant future where, due to worsening global environmental collapse, an artificial intelligence determines that the planet would be better off without the presence of humans. After a virus that sterilizes the entire human population is released, humanity must reckon with how they leave this world before…
I taught myself to code back in 1994 while working the graveyard shift as a geologist in the environmental industry. My job consisted of sitting in a chair during the dark hours of the night in a shopping center in Stockton, CA, watching another geologist take samples from wells in the parking lot. A friend of mine suggested I learn to code because I liked computers. I don’t mean to make this out to be a “it’s so simple anyone can do it!” You need to have a relentless drive to learn, which is why I wrote my book, The Imposter’s Handbook - as an active step to learning what I didn’t know I didn’t know.
You’ve heard of Einstein, Turing, Newton, and Hawking - but do you know who Claude Shannon is? Would you be surprised if I told you that he’s probably done more for our current way of life than all of the others combined? It’s true, and it’s unbelievable.
Claude Shannon was a quiet, quirky man who had what you might call The Most Genius Move of the last foreveryears: he took an obscure discipline of mathematics (Boolean Algebra) and applied it to electrical circuits, creating the digital circuit in the process. If you’ve ever wondered how 1s and 0s are turned into if statements and for loops - well here you go.
Oh, but that’s just the beginning. Dr. Shannon took things much further when he described how these 1s and 0s could be transmitted from point A to point B without loss of data. This was a big problem…
Winner of the Neumann Prize for the History of Mathematics
**Named a best book of the year by Bloomberg and Nature**
**'Best of 2017' by The Morning Sun**
"We owe Claude Shannon a lot, and Soni & Goodman’s book takes a big first step in paying that debt." —San Francisco Review of Books
"Soni and Goodman are at their best when they invoke the wonder an idea can instill. They summon the right level of awe while stopping short of hyperbole." —Financial Times
"Jimmy Soni and Rob Goodman make a convincing case for their subtitle while reminding us that Shannon…
