Machine learning: Trends, perspectives, and prospects
SciencePublished 16 July 2015
Michael I. Jordan, Tom M. Mitchell
Citations9,585
SJR quartileQ1
SJR score10.42
SNIP6.62
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
The adoption of data-intensive machine-learning methods can be found throughout science, technology and commerce, leading to more evidence-based decision-making across many walks of life, including health care, manufacturing, education, financial modeling, policing, and marketing.
Abstract
Machine learning addresses the question of how to build computers that improve automatically through experience. It is one of today's most rapidly growing technical fields, lying at the intersection of computer science and statistics, and at the core of artificial intelligence and data science. Recent progress in machine learning has been driven both by the development of new learning algorithms and theory and by the ongoing explosion in the availability of online data and low-cost computation. The adoption of data-intensive machine-learning methods can be found throughout science, technology and commerce, leading to more evidence-based decision-making across many walks of life, including health care, manufacturing, education, financial modeling, policing, and marketing.
Keywords
Computer Science
Communications of the ACMImageNet classification with deep convolutional neural networks
75,709 Citations2017Alex Krizhevsky, Ilya Sutskever +1 more
A large, deep convolutional neural network was trained to classify the 1.2 million high-resolution images in the ImageNet LSVRC-2010 contest into the 1000 different classes and employed a recently developed regularization method called "dropout" that proved to be very effective.
NatureHuman-level control through deep reinforcement learning
29,984 Citations2015Volodymyr Mnih, Koray Kavukcuoglu +17 more
This work bridges the divide between high-dimensional sensory inputs and actions, resulting in the first artificial agent that is capable of learning to excel at a diverse array of challenging tasks.
ScienceReducing the Dimensionality of Data with Neural Networks
20,953 Citations2006Geoffrey E. Hinton, Ruslan Salakhutdinov
The Elements of Statistical Learning: Data Mining, Inference, and Prediction
19,345 Citations2013Trevor Hastie, Robert Tibshirani +1 more
Neural NetworksDeep learning in neural networks: An overview
18,033 Citations2014Jürgen Schmidhuber
This historical survey compactly summarizes relevant work, much of it from the previous millennium, review deep supervised learning, unsupervised learning, reinforcement learning & evolutionary computation, and indirect search for short programs encoding deep and large networks.
Foundations and Trends® in Machine LearningDistributed Optimization and Statistical Learning via the Alternating Direction Method of Multipliers
15,983 Citations2011Stephen Boyd, Neal Parikh +3 more
IEEE Signal Processing MagazineDeep Neural Networks for Acoustic Modeling in Speech Recognition: The Shared Views of Four Research Groups
10,313 Citations2012Geoffrey E. Hinton, Li Deng +9 more
ScienceA Neural Substrate of Prediction and Reward
9,610 Citations1997Wolfram Schultz, Peter Dayan +1 more
Findings in this work indicate that dopaminergic neurons in the primate whose fluctuating output apparently signals changes or errors in the predictions of future salient and rewarding events can be understood through quantitative theories of adaptive optimizing control.
Machine learning: a probabilistic perspective
9,297 Citations2012Kevin P. Murphy
Lecture notes in computer scienceCalibrating Noise to Sensitivity in Private Data Analysis
7,028 Citations2006Cynthia Dwork, Frank McSherry +2 more
Communications of the ACMProbabilistic topic models
5,549 Citations2012David M. Blei
Surveying a suite of algorithms that offer a solution to managing large document archives suggests they are well-suited to handle large amounts of data.
A theory of the learnable
4,242 Citations1984Leslie G. Valiant
This paper regards learning as the phenomenon of knowledge acquisition in the absence of explicit programming, and gives a precise methodology for studying this phenomenon from a computational viewpoint.
Communications of the ACMA theory of the learnable
3,268 Citations1984Leslie G. Valiant
This paper regards learning as the phenomenon of knowledge acquisition in the absence of explicit programming, and gives a precise methodology for studying this phenomenon from a computational viewpoint.
Journal of Machine Learning ResearchTransfer Learning for Reinforcement Learning Domains: A Survey
1,560 Citations2009Matthew E. Taylor, Peter Stone
This article presents a framework that classifies transfer learning methods in terms of their capabilities and goals, and then uses it to survey the existing literature, as well as to suggest future directions for transfer learning work.
Learning to Learn
1,281 Citations1998Jonathan Baxter, Lorien Pratt
This chapter discusses Reinforcement Learning with Self-Modifying Policies J. Schmidhuber, et al., and theoretical Models of Learning to Learn J. Baxter, a first step towards Continual Learning.
The MIT Press eBooksOptimization for Machine Learning
897 Citations2011Suvrit Sra
This book captures the state of the art of the interaction between optimization and machine learning in a way that is accessible to researchers in both fields and will enrich the ongoing cross-fertilization between the machine learning community and these other fields, and within the broader optimization community.
Chapman & Hall/CRC data mining and knowledge discovery seriesRandomized Algorithms for Matrices and Data
447 Citations2012Michael W. Mahoney
Journal of the Royal Statistical Society Series B (Statistical Methodology)A Scalable Bootstrap for Massive Data
400 Citations2014Ariel Kleiner, Ameet Talwalkar +2 more
The ‘bag of little bootstraps’ (BLB) is introduced, which is a new procedure which incorporates features of both the bootstrap and subsampling to yield a robust, computationally efficient means of assessing the quality of estimators.
PLoS ONESimultaneously Uncovering the Patterns of Brain Regions Involved in Different Story Reading Subprocesses
274 Citations2014Leila Wehbe, Brian Murphy +4 more
This approach is the first to simultaneously track diverse reading subprocesses during complex story processing and predict the detailed neural representation of diverse story features, ranging from visual word properties to the mention of different story characters and different actions they perform.
Journal of the ACMLinear-Time Approximation for Maximum Weight Matching
270 Citations2014Ran Duan, Seth Pettie
This article gives an algorithm that computes a (1 − 1 − 0))-approximate maximum weight matching in O(i) time, that is, optimal linear time for any fixed ε, and should be appealing in all applications that can tolerate a negligible relative error.
The Annals of StatisticsOptimal detection of sparse principal components in high dimension
263 Citations2013Quentin Berthet, Philippe Rigollet
The minimax optimal test is based on a sparse eigenvalue statistic, and a computationally efficient alternative test using convex relaxations is described, which is proved to detect sparse principal components at near optimal detection levels and performs well on simulated datasets.
Journal of the ACMA learning theory approach to noninteractive database privacy
260 Citations2013Avrim Blum, Katrina Ligett +1 more
It is shown that, ignoring computational constraints, it is possible to release synthetic databases that are useful for accurately answering large classes of queries while preserving differential privacy and a relaxation of the utility guarantee is given.
Foundations and Trends® in Machine LearningRandomized Algorithms for Matrices and Data
211 Citations2011Michael W. Mahoney Boyd
Proceedings of the National Academy of SciencesComputational and statistical tradeoffs via convex relaxation
192 Citations2013Venkat Chandrasekaran, Michael I. Jordan
This paper defines a notion of “algorithmic weakening,” in which a hierarchy of algorithms is ordered by both computational efficiency and statistical efficiency, allowing the growing strength of the data at scale to be traded off against the need for sophisticated processing.
Journal of the ACMPrivacy Aware Learning
182 Citations2014John C. Duchi, Michael I. Jordan +1 more
This work establishes sharp upper and lower bounds on the convergence rates of statistical estimation procedures in a local privacy framework and exhibits a precise tradeoff between the amount of privacy the data preserves and the utility of any statistical estimator or learning procedure.
arXiv (Cornell University)Distributed Learning, Communication Complexity and Privacy
114 Citations2012Maria-Florina Balcan, Avrim Blum +2 more
SIAM Journal on ComputingComputational Sample Complexity
30 Citations2000Scott E. Decatur, Oded Goldreich +1 more
Wiley Encyclopedia of Operations Research and Management SciencePartially Observable<scp>MDPs</scp>(<scp>POMDPS</scp>): Introduction and Examples
6 Citations2011Emine Yaylalı, Julie S. Ivy
POMDPs are introduced and the relationship between Markov models and PomDPs is discussed and a wide range of POMDP applications from the literature are presented.