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. The text offers mathematical and conceptual background, covering relevant concepts in linear algebra, probability theory and information theory, numerical computation, and machine learning. It describes deep learning techniques used by practitioners in industry, including deep feedforward networks, regularization, optimization algorithms, convolutional networks, sequence modeling, and practical methodology; and it surveys such applications as natural language processing, speech recognition, computer vision, online recommendation systems, bioinformatics, and videogames. Finally, the book offers research perspectives, covering such theoretical topics as linear factor models, autoencoders, representation learning, structured probabilistic models, Monte Carlo methods, the partition function, approximate inference, and deep generative models. Deep Learning can be used by undergraduate or graduate students planning careers in either industry or research, and by software engineers who want to begin using deep learning in their products or platforms. A website offers supplementary material for both readers and instructors.

Deep Learning

Reinforcement learning, one of the most active research areas in artificial intelligence, is a computational approach to learning whereby an agent tries to maximize the total amount of reward it receives when interacting with a complex, uncertain environment. In Reinforcement Learning, Richard Sutton and Andrew Barto provide a clear and simple account of the key ideas and algorithms of reinforcement learning. Their discussion ranges from the history of the field's intellectual foundations to the most recent developments and applications. The only necessary mathematical background is familiarity with elementary concepts of probability. The book is divided into three parts. Part I defines the reinforcement learning problem in terms of Markov decision processes. Part II provides basic solution methods: dynamic programming, Monte Carlo methods, and temporal-difference learning. Part III presents a unified view of the solution methods and incorporates artificial neural networks, eligibility traces, and planning; the two final chapters present case studies and consider the future of reinforcement learning.

/pdf/reinforcement-learning-an-introduction-rzxgej9p17.pdf

Reinforcement Learning: An Introduction

In the first part of the paper we consider the problem of dynamically apportioning resources among a set of options in a worst-case on-line framework. The model we study can be interpreted as a broad, abstract extension of the well-studied on-line prediction model to a general decision-theoretic setting. We show that the multiplicative weight-update Littlestone?Warmuth rule can be adapted to this model, yielding bounds that are slightly weaker in some cases, but applicable to a considerably more general class of learning problems. We show how the resulting learning algorithm can be applied to a variety of problems, including gambling, multiple-outcome prediction, repeated games, and prediction of points in Rn. In the second part of the paper we apply the multiplicative weight-update technique to derive a new boosting algorithm. This boosting algorithm does not require any prior knowledge about the performance of the weak learning algorithm. We also study generalizations of the new boosting algorithm to the problem of learning functions whose range, rather than being binary, is an arbitrary finite set or a bounded segment of the real line.

/pdf/a-decision-theoretic-generalization-of-on-line-learning-and-3ykfx1u7er.pdf

A Decision-Theoretic Generalization of On-Line Learning and an Application to Boosting

https://www2.econ.iastate.edu/tesfatsi/DeepLearningInNeuralNetworksOverview.JSchmidhuber2015.pdf

Deep learning in neural networks

The game of Go has long been viewed as the most challenging of classic games for artificial intelligence owing to its enormous search space and the difficulty of evaluating board positions and moves. Here we introduce a new approach to computer Go that uses ‘value networks’ to evaluate board positions and ‘policy networks’ to select moves. These deep neural networks are trained by a novel combination of supervised learning from human expert games, and reinforcement learning from games of self-play. Without any lookahead search, the neural networks play Go at the level of stateof-the-art Monte Carlo tree search programs that simulate thousands of random games of self-play. We also introduce a new search algorithm that combines Monte Carlo simulation with value and policy networks. Using this search algorithm, our program AlphaGo achieved a 99.8% winning rate against other Go programs, and defeated the human European Go champion by 5 games to 0. This is the first time that a computer program has defeated a human professional player in the full-sized game of Go, a feat previously thought to be at least a decade away.

/pdf/mastering-the-game-of-go-with-deep-neural-networks-and-tree-3viuxo6uxm.pdf

Mastering the game of Go with deep neural networks and tree search

This paper presents Phantom, a simple constant space algorithm for rate based flow control. As shown by our simulations, it converges fast to a fair rate allocation while generating a moderate queue length. While our approach can be easily implemented in ATM switches for managing ABR traffic, it is also suitable for flow control in TCP router based networks. Both the introduced overhead and the required modifications in TCP flow control systems are minimal. The implementation of this approach in TCP guarantees fairness and provides a unifying interconnection between TCP routers and ATM networks. The new algorithm easily inter-operates with current TCP flow control mechanisms and thus can be gradually introduced into installed based TCP networks.

Phantom: a simple and effective flow control scheme

We consider a network providing Differentiated Services (Diffserv) which allow Internet service providers (ISP) to offer different levels of Quality of Service (QoS) to different traffic streams. We study FIFO buffering algorithms, where packets must be transmitted in the order they arrive. The buffer space is limited, and packets are lost if the buffer is full. Each packet has an intrinsic value, and the goal is to maximize the total value of transmitted packets. Our main contribution is an algorithm for arbitrary packet values that for the first time achieves a competitive ratio better than 2, namely 2 - e for a constant e > 0.

Improved competitive guarantees for QoS buffering

Results on learnability and the Vapnik-Chervonenkis dimension (Extended Abstract)

We consider a model of robust learning in an adversarial environment. The learner gets uncorrupted training data with access to possible corruptions that may be effected by the adversary during testing. The learner's goal is to build a robust classifier, which will be tested on future adversarial examples. The adversary is limited to $k$ possible corruptions for each input. We model the learner-adversary interaction as a zero-sum game. This model is closely related to the adversarial examples model of Schmidt et al. (2018); Madry et al. (2017). Our main results consist of generalization bounds for the binary and multiclass classification, as well as the real-valued case (regression). For the binary classification setting, we both tighten the generalization bound of Feige, Mansour, and Schapire (2015), and are also able to handle infinite hypothesis classes. The sample complexity is improved from $O(\frac{1}{\epsilon^4}\log(\frac{|\mathcal{H}|}{\delta}))$ to $O\big(\frac{1}{\epsilon^2}(\sqrt{k \mathrm{VC}(\mathcal{H})}\log^{\frac{3}{2}+\alpha}(k\mathrm{VC}(\mathcal{H}))+\log(\frac{1}{\delta})\big)$ for any $\alpha > 0$. Additionally, we extend the algorithm and generalization bound from the binary to the multiclass and real-valued cases. Along the way, we obtain results on fat-shattering dimension and Rademacher complexity of $k$-fold maxima over function classes; these may be of independent interest. 
For binary classification, the algorithm of Feige et al. (2015) uses a regret minimization algorithm and an ERM oracle as a black box; we adapt it for the multiclass and regression settings. The algorithm provides us with near-optimal policies for the players on a given training sample.

/pdf/improved-generalization-bounds-for-robust-learning-4a6kgg5dea.pdf

Improved Generalization Bounds for Robust Learning.

: An important function of communication networks is to implement reliable data transfer over an unreliable underlying network. Formal specifications are given for reliable and unreliable communication layers, in terms of I/O automata. Based on these specifications, it is proved that no reliable communication protocol can tolerate crashes of the processors on which the protocol runs.

Yishay Mansour

Papers

Phantom: a simple and effective flow control scheme

Improved competitive guarantees for QoS buffering

Results on learnability and the Vapnik-Chervonenkis dimension (Extended Abstract)

Improved Generalization Bounds for Robust Learning.

The impossibility of implementing reliable communication in the face of crashes