Deep Learning Reading List: The Essentials

The summer is always that time of year when you pick up a book and actually realise how much you enjoy reading. Sat by the pool, or in your garden with a book in one hand and drink in the other, but this year we’re making it our mission at RE•WORK to keep reading throughout the winter months, and we’d like you to join us.

We’ve spoken to some of our AI community to ask what Deep Learning books, journals and papers they’d recommend, and we’ve compiled a list:

Books

Deep Learning (Adaptive Computation and Machine Learning Series), Ian Goodfellow and Yoshua Benigo

Both Ian Goodfellow and Yoshua Bengio have given presentations, interviews, and appeared on panel discussions at previous RE•WORK Summits. In January in San Francisco, Goodfellow held a book signing of the much anticipated book.

An introduction to a broad range of topics in deep learning, covering mathematical and conceptual background, deep learning techniques used in industry, and research perspectives. "Written by three experts in the field, Deep Learning is the only comprehensive book on the subject." -Elon Musk, co-chair of OpenAI; co-founder and CEO of Tesla and SpaceX Deep learning is a form of machine learning that enables computers to learn from experience and understand the world in terms of a hierarchy of concepts. Because the computer gathers knowledge from experience, there is no need for a human computer operator to formally specify all the knowledge that the computer needs. The hierarchy of concepts allows the computer to learn complicated concepts by building them out of simpler ones; a graph of these hierarchies would be many layers deep. This book introduces a broad range of topics in deep learning.

Hands-On Machine Learning with Scikit-Learn & TensorFlow , Aurelien Geron

Suggested by Francis Z Lin, BNY Mellon, who will be speaking at the AI in Finance Summit, New York, September 6 - 7

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.

TensorFlow 1.x Deep Learning Cookbook: Over 90 unique recipes to solve artificial-intelligence driven problems with Python, Antonio Gulli, Amita Kapoor

Suggested by Francis Z Lin, BNY Mellon

In this book, you will learn how to efficiently use TensorFlow, Google's open source framework for deep learning. You will implement different deep learning networks such as Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), Deep Q-learning Networks (DQNs), and Generative Adversarial Networks (GANs) with easy to follow independent recipes. You will learn how to make Keras as backend with TensorFlow. With a problem-solution approach, you will understand how to implement different deep neural architectures to carry out complex tasks at work.

Deep Learning: A Practitioner's Approach, Adam Gibson and Josh Patterson

If you’re interested in applying AI and DL to your business, also check out RE•WORK’s white paper; Should you be using AI in your Business?

How can machine learning—especially deep neural networks—make a real difference in your organization? This hands-on guide not only provides the most practical information available on the subject, but also helps you get started building efficient deep learning networks.

Authors Adam Gibson and Josh Patterson provide theory on deep learning before introducing their open-source Deeplearning4j (DL4J) library for developing production-class workflows. Through real-world examples, you’ll learn methods and strategies for training deep network architectures and running deep learning workflows on Spark and Hadoop with DL4J.

Pattern Classification, Second Edition, Richard O. Duda, Peter E. Hart, David G. Stork

The first edition, published in 1973, has become a classic reference in the field. Now with the second edition, readers will find information on key new topics such as neural networks and statistical pattern recognition, the theory of machine learning, and the theory of invariances. Also included are worked examples, comparisons between different methods, extensive graphics, expanded exercises and computer project topics.

Neural Networks and Deep Learning,  Antonio Gulli and Sujit Pal

Neural Networks and Deep Learning is a free online book. The book will teach you about:

• Neural networks, a beautiful biologically-inspired programming paradigm which enables a computer to learn from observational data
• Deep learning, a powerful set of techniques for learning in neural networks

Neural networks and deep learning currently provide the best solutions to many problems in image recognition, speech recognition, and natural language processing. This book will teach you many of the core concepts behind neural networks and deep learning.

Deep Learning with Python, Francois Chollet

Deep Learning with Python introduces the field of deep learning using the Python language and the powerful Keras library. Written by Keras creator and Google AI researcher François Chollet, this book builds your understanding through intuitive explanations and practical examples. You'll explore challenging concepts and practice with applications in computer vision, natural-language processing, and generative models. By the time you finish, you'll have the knowledge and hands-on skills to apply deep learning in your own projects.

Artificial Intelligence – A Modern Approach and Machine Learning – An Algorithmic Perspective, Stephen Marsland

The book covers neural networks, graphical models, reinforcement learning, evolutionary algorithms, dimensionality reduction methods, and the important area of optimization. It treads the fine line between adequate academic rigour and overwhelming students with equations and mathematical concepts. The author addresses the topics in a practical way while providing complete information and references where other expositions can be found. He includes examples based on widely available datasets and practical and theoretical problems to test understanding and application of the material. The book describes algorithms with code examples backed up by a website that provides working implementations in Python. The author uses data from a variety of applications to demonstrate the methods and includes practice problems for students to solve.

Papers

3D Steerable CNNs: Learning Rotationally Equivariant Features in Volumetric, Maurice Weiler, Mario Geiger, Max Welling, Wouter Boomsma, Taco Cohen

Taco Cohen, ML Researcher Scientist at Qualcomm Research Netherlands key contributor to this paper, will be presenting his most recent work at the Deep Learning Summit in London, September 20 - 21

This paper presents a convolutional network that is equivariant to rigid body motions. The model uses scalar-, vector-, and tensor fields over 3D Euclidean space to represent data, and equivariant convolutions to map between such representations. These SE(3)-equivariant convolutions utilize kernels which are parameterized as a linear combination of a complete steerable kernel basis, which is derived in this paper. We prove that equivariant convolutions are the most general equivariant linear maps between fields over R^3. Our experimental results confirm the effectiveness of 3D Steerable CNNs for the problem of amino acid propensity prediction and protein structure classification, both of which have inherent SE(3) symmetry.

Imagination Machines: A New Challenge for Artificial Intelligence, Sridhar Mahadevan

Sridhar Mahadevan, Director of Data Science at Adobe Research will be hosting a workshop on ‘Envisioning the Future Beyond Deep Learning’ at the Deep Learning Summit in San Francisco this January 24 - 25

The aim of this paper is to propose a new overarching challenge for AI: the design of imagination machines. Imagination has been defined as the capacity to mentally transcend time, place, and/or circumstance. Much of the success of AI currently comes from a revolution in data science, specifically the use of deep learning neural networks to extract structure from data. This paper argues for the development of a new field called imagination science, which extends data science beyond its current realm of learning probability distributions from samples.

Intelligence without representation, Rodney A. Brooks

Sergey Levine, who spoke at the Deep Learning Summit in San Francisco this January, recommends the following paper.

Artificial intelligence research has foundered on the issue of representation. When intelligence is approached in an incremental manner, with strict reliance on interfacing to the real world through perception and action, reliance on representation disappears. In this paper we outline our approach to incrementally building complete intelligent Creatures. The fundamental decomposition of the intelligent system is not into independent information processing units which must interface with each other via representations. Instead, the intelligent system is decomposed into independent and parallel activity producers which all interface directly to the world through perception and action, rather than interface to each other particularly much. The notions of central and peripheral systems evaporate everything is both central and peripheral. Based on these principles we have built a very successful series of mobile robots which operate without supervision as Creatures in standard office environments.

Want to learn more from the authors of these publications and global experts? Register for any upcoming RE•WORK Summit with the code SUMMER before September 7th to save a huge 25% off all summits (excluding dinners).