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

Ads on the Internet are increasingly sold via ad exchanges such as RightMedia, AdECN and Doubleclick Ad Exchange. These exchanges allow real-time bidding, that is, each time the publisher contacts the exchange, the exchange "calls out" to solicit bids from ad networks. This solicitation introduces a novel aspect, in contrast to existing literature. This suggests developing a joint optimization framework which optimizes over the allocation and well as solicitation.

We model this selective call out as an online recurrent Bayesian decision framework with bandwidth type constraints. We obtain natural algorithms with bounded performance guarantees for several natural optimization criteria. We show that these results hold under different call out constraint models, and different arrival processes. Interestingly, the paper shows that under MHR assumptions, the expected revenue of generalized second price auction with reserve is constant factor of the expected welfare. Also the analysis herein allow us prove adaptivity gap type results for the adwords problem.

Selective call out and real time bidding

We study how to efficiently diffuse updates to a large distributed system of data replicas, some of which may exhibit arbitrary (Byzantine) failures. We assume that strictly fewer than t replicas fail, and that each update is initially received by at least t correct replicas. The goal is to diffuse each update to all correct replicas while ensuring that correct replicas accept no updates generated spuriously by faulty replicas. To achieve reliable diffusion, each correct replica accepts an update only after receiving it from at least t others. We provide the first analysis of epidemic-style protocols for such environments. This analysis is fundamentally different from known analyses for the benign case due to our treatment of fully Byzantine failure-which, among other things, precludes the use of digital signatures for authenticating forwarded updates. We propose two epidemic-style diffusion algorithms and two measures that characterize the efficiency of diffusion algorithms in general. We characterize both of our algorithms according to these measures, and also prove lower bounds with regards to these measures that show that our algorithms are close to optimal.

On diffusing updates in a Byzantine environment

Harmonic buffer management policy for shared memory switches

This work studies external regret in sequential prediction games with arbitrary payoffs (nonnegative or non-positive). External regret measures the difference between the payoff obtained by the forecasting strategy and the payoff of the best action. We focus on two important parameters: M, the largest absolute value of any payoff, and Q*, the sum of squared payoffs of the best action. Given these parameters we derive first a simple and new forecasting strategy with regret at most order of $\sqrt{Q^{*}({\rm ln}N)}+M {\rm ln} N$, where N is the number of actions. We extend the results to the case where the parameters are unknown and derive similar bounds. We then devise a refined analysis of the weighted majority forecaster, which yields bounds of the same flavour. The proof techniques we develop are finally applied to the adversarial multi-armed bandit setting, and we prove bounds on the performance of an online algorithm in the case where there is no lower bound on the probability of each action.

/pdf/improved-second-order-bounds-for-prediction-with-expert-1pjemh0val.pdf

Improved second-order bounds for prediction with expert advice

The authors study the problem of on-line call control, i.e., the problem of accepting or rejecting an incoming call without knowledge of future calls. The problem is part of the more general problem of bandwidth allocation and management. Intuition suggests that knowledge of future call arrivals can be crucial to the performance of the system. They present on-line call control algorithms that, in some circumstances, are competitive, i.e., perform (up to a constant factor) as well as their off-line, clairvoyant counterparts. They also prove the optimality of some algorithms. The model is that of a line of nodes, and they investigate a variety of cases concerning the value of the calls. The value is gained only if the call terminates successfully, otherwise-if the call is rejected, or prematurely terminated-no value is gained. The performance of the algorithm is then measured by the cumulative value achieved, when given a sequence of calls. The variety of call value criteria captures the most natural cost assignments to network services. >

Yishay Mansour

Papers

Selective call out and real time bidding

On diffusing updates in a Byzantine environment

Harmonic buffer management policy for shared memory switches

Improved second-order bounds for prediction with expert advice

Efficient on-line call control algorithms