Skip to content
Machine Learning SalonFree learning resources

Research

Academics

Researchers, professors and free access to research papers across the field.

Cambridge University Publications page

mlg.eng.cam.ac.uk

Google Scholar

Stand on the shoulders of giants.

Google Scholar provides a simple way to broadly search for scholarly literature. From one place, you can search across many disciplines and sources: articles, theses, books, abstracts and court opinions, from academic publishers, professional societies, online repositories, universities and other web sites. Google Scholar helps you find relevant work across the world of scholarly research.

scholar.google.com

scholar.google.com

Google Research

Google publishes hundreds of research papers each year. Publishing is important to us; it enables us to collaborate and share ideas with, as well as learn from, the broader scientific community. Submissions are often made stronger by the fact that ideas have been tested through real product implementation by the time of publication.

research.google.com

Yahoo Research

The machine learning group is a team of experts in computer science, statistics, mathematical optimization, and automatic control. They focus on making computers learn abstractions, patterns, conditional probability distributions, and policies from web scale data with the goal to improve the online experience for Yahoo! users, partner publishers, and advertisers.

Machine learning has such a broad influence on the internet, it can be quite difficult to recognize. Machine learning’s benefits are often hidden, they are the spam emails you don’t see, the uninteresting news articles you don’t see, and the irrelevant search results you don’t see, just to name a new. Machine learning is one of the best technologies we have for solving some of the biggest problems on the Web.

labs.yahoo.com

Microsoft Research

The Machine Learning Groups of Microsoft Research include a set of researchers and developers who push the state of the art in machine learning. We span the space from proving theorems about the math underlying ML, to creating new ML systems and algorithms, to helping our partner product groups apply ML to large and complex data sets.

research.microsoft.com

Journal from MIT Press

The Journal of Machine Learning Research (JMLR) provides an international forum for the electronic and paper publication of high quality scholarly articles in all areas of machine learning. All published papers are freely available online.

jmlr.org

INRIA

Access to Research Papers

haltools.inrialpes.fr

More to be added ...

AMERICA, US

Andrew Ng, Stanford University

Andrew Ng is a Co founder of Coursera and the Director of the Stanford AI Lab. In 2011 he led the development of Stanford University’s main MOOC (Massive Open Online Courses) platform and also taught an online Machine Learning class that was offered to over 100,000 students, leading to the founding of Coursera.

Ng’s goal is to give everyone in the world access to a high quality education, for free. Today, Coursera partners with some of the top universities in the world to offer high quality free online courses. It is the largest MOOC platform in the world.

Outside online education, Ng’s work at Stanford is on machine learning with an emphasis on deep learning. He also founded and led a project at Google to develop massive scale deep learning algorithms. It resulted in the famous cat detector popularly known as the “Google cat” in which a massive neural network with 1 billion parameters learned from unlabeled YouTube videos.

cs.stanford.edu

Judea Pearl, Cognitive System Laboratory, UCLA

Judea Pearl (born 1936) is an Israeli born American computer scientist and philosopher, best known for championing the probabilistic approach to artificial intelligence and the development of Bayesian networks (see the article on belief propagation). He is also credited for developing a theory of causal and counterfactual inference based on structural models (see article on causality). He is the 2011 winner of the ACM Turing Award, the highest distinction in computer science, "for fundamental contributions to artificial intelligence through the development of a calculus for probabilistic and causal reasoning". (source Wikipedia)

bayes.cs.ucla.edu

Hal Daume III, University of Maryland

I am Hal Daumé III, an Associate Professor in Computer Science (also UMIACS and Linguistics) at the University of Maryland; I was previously in the School of Computing at the University of Utah (CV). Although I'd like to be known for my research in language (computational linguistics and natural language processing) and machine learning (structured prediction, domain adapation and Bayesian methods), I am probably best known for my NLPers blog. I associate myself most with conferences like ACL, ICML, EMNLP and NIPS. At UMD, I'm affiliated with the Computational Linguistics lab, the machine learning reading group, the language science program and the AI group, and interact closely with LINQS and computer vision.

hal3.name

More to be added ...

AMERICA, CANADA

Yoshua Bengio, University of Montreal

My long term goal is to understand intelligence; understanding the underlying principles would deliver artificial intelligence, and I believe that learning algorithms are essential in this quest.

Machine learning algorithms attempt to endow machines with the ability to capture operational knowledge through examples, e.g., allowing a machine to classify or predict correctly in new cases. Machine learning research has been extremely successful in the past two decades and is now applied in many areas of science and technology, some well known examples including web search engines, natural language translation, speech recognition, machine vision, and data mining. Yet, machines still seem to fall short of even mammal level intelligence in many respects. One of the remaining frontiers of machine learning is the difficulty of learning the kind of complicated and highly varying functions that are necessary to perform machine vision or natural language processing tasks at a level comparable to humans (even a two year old).

See my lab's long term vision web page for a broader introduction.

An introductory discussion of recent and ongoing research is below. See the lab's publications site for a downloadable and complete bibliographic list of my papers.

www.iro.umontreal.ca

www.iro.umontreal.ca

www.iro.umontreal.ca

Hugo Larochelle, Universite de Sherbrooke

Je m'intéresse aux algorithmes d'apprentissage automatique, soit aux algorithmes capables d'extraire des concepts ou patrons à partir de données. Mes travaux se concentrent sur le développement d'approches connexionnistes et probabilistes à diverses problèmes d'intelligence artificielle, tels la vision artificielle et le traitement automatique du langage.

Les thèmes de recherche auxquels je m'intéresse incluent:

Problèmes: apprentissage supervisé, semi supervisé et non supervisé, prédiction de cibles structurées, ordonnancement, estimation de densité;

Modèles: réseaux de neurones profonds («deep learning»), autoencodeurs, machines de Boltzmann, champs Markoviens aléatoires;

Applications: reconnaissance et suivi d'objects, classification et ordonnancement de documents.

www.dmi.usherb.ca

info.usherbrooke.ca

More to be added ...

EUROPE, FRANCE

Francis Bach, Ecole Normale Superieure

www.di.ens.fr

More to be added ...

EUROPE, UK

Mark Herbster, University College London

My research currently focuses on the problem of predicting a labeling of a graph. This problem is foundational for transductive and semi supervised learning. Initial bounds and experimental results are given in Online learning over graphs. The paper Prediction on a graph with a perceptron significantly improves on previous results in terms of the tightness and interpretability of the bounds. In the recent work A fast method to predict the labeling of a tree we've developed methods to speed up graph prediction methods. I am also broadly interested in online learning, see my publications page for more details.

www0.cs.ucl.ac.uk

David Barber, University College London

David Barber received a BA in Mathematics from Cambridge University and subsequently a PhD in Theoretical Physics (Statistical Mechanics) from Edinburgh University. He is currently Reader in Information Processing in the department of Computer Science UCL where he develops novel information processing schemes, mainly based on the application of probabilistic reasoning. Prior to joining UCL he was a lecturer at Aston and Edinburgh Universities.

web4.cs.ucl.ac.uk

Gabriel Brostow, University College London

My name is Gabriel Brostow, and I am an associate professor (Senior Lecturer) in Computer Science here at UCL. My group explores research problems relating to Computer Vision and Computer Graphics. The students and colleagues here have diverse interests, but my focus is on "Smart Capture" for analysis and synthesis applications. To me, smart capture of visual data (usually video) means having or finding satisfying answers to these questions about a system, whether interactive or fully automated:

I) Does the system know the intended purpose of the data being captured?

II) Can the system assess its own accuracy?

III) Does the system compare new inputs to old ones?

I love this field because it allows us to apply our expertise to a variety of tough problems, including film and photo special effects (computational photography), action analysis (of people, animals, and cells), and authoring systems (for architecture, animation, presentations) that make the most of user effort. "Motion reveals everything" used to be my main research mantra, but that has now taken hold sufficiently (obviously NOT just through my efforts!) that it no longer needs championing.

www0.cs.ucl.ac.uk

Jun Wang, University College London

My research focus is on the areas of information retrieval, large scale data mining, multimedia content analysis, and statistical pattern recognition; current research covers both theoretical and practical aspects:

portfolio theory and statistical modeling of information retrieval,

data mining and collaborative filtering (recommendation),

web economy and online advertising,

user centric information seeking,

social, “the wisdom of crowds”, approaches for content understanding, organisation, and retrieval,

peer to peer information retrieval and filtering, and

multimedia content analysis, indexing and retrieval.

scholar.google.com

David Jones Lab, University College London

My main research interests are in protein structure prediction and analysis, simulations of protein folding, Hidden Markov Model methods, transmembrane protein analysis, machine learning applications in bioinformatics, de novo protein design methodology, and genome analysis including the application of intelligent software agents. New areas of research include the use of high throughput computing and Grid technology for bioinformatics applications, analysis and prediction of protein disorder, expression array data analysis and the analysis and prediction of protein function and protein protein interactions.

bioinf.cs.ucl.ac.uk

Simon Prince, University College London

My initial work addressed human stereo vision. My doctoral thesis concerned the solution of the binocular stereo correspondence problem in the human visual system. I also worked on the physiology of stereo vision in my subsequent post doctoral research.

I became interested in computer vision and made the switch in 2000. My first Computer Science research was on time series methods for the solution of the inverse problem in Optical Tomography with Simon Arridge at UCL. In Singapore, I worked for several years on augmented reality. This involved developing algorithms for camera pose estimation, and a three dimensional video conferencing system using real time image based rendering.

More recently, I have worked on face detection in a novel foveated sensor system. I am interested in face recognition in general and have presented work on how to recognize faces in the presence of large pose and lighting changes.

I am interested in most areas of computer vision and computer graphics, and still maintain active links with the neuroscience and medical imaging communities.

web4.cs.ucl.ac.uk

www.computervisionmodels.com

Massimiliano Pontil, University College London

I am mainly interested in machine learning theory and pattern recognition. I have also some interest in function representation and approximation, numerical optimization and statistics. I have worked on different machine learning approaches, particularly on regularization methods, such as support vector machines and other kernel based methods, multi task and transfer learning, online learning and learning over graphs. I have also worked on machine learning applications arising in computer vision, natural language processing, bioinformatics and user modeling.

www0.cs.ucl.ac.uk

Richard E Turner, Cambridge University

Richard Turner holds a Lectureship (equivalent to US Assistant Professor) in Computer Vision and Machine Learning in the Computational and Biological Learning Lab, Department of Engineering, University of Cambridge, UK. Before taking up this position, he held an EPSRC Postdoctoral research fellowship which he spent at both the University of Cambridge and the Laboratory for Computational Vision, NYU, USA. He has a PhD degree in Computational Neuroscience and Machine Learning from the Gatsby Computational Neuroscience Unit, UCL, UK and a M.Sci. degree in Natural Sciences (specialism Physics) from the University of Cambridge, UK.

scholar.google.com

Phil Blunsom, Oxford University

My research interests lie at the intersection of machine learning and computational linguistics. I apply machine learning techniques, such as graphical models, to a range of problems relating to the understanding, learning and manipulation of language. Recently I have focused on structural induction problems such as grammar induction and learning statistical machine translation models

scholar.google.co.uk

Nando de Freitas, Oxford University

I want to understand intelligence and how minds work. My research is multidisciplinary and focuses primarily on the following areas:

Machine learning, big data, and computational statistics

Artificial intelligence, probabilistic reasoning, and decision making

Computational neuroscience, neural networks, and cognitive science

Randomized algorithms, and Monte Carlo simulation

Vision, robotics, and speech perception

scholar.google.co.uk

Karl Hermann, Oxford University

My research is at the intersection of Natural Language Processing and Machine Learning, with particular emphasis on semantics. Current topics of interest include:

Compositional Semantics

Learning from Multilingual Data

Semantic Frame Identification

Machine Translation

Hypergraph Grammars

www.cs.ox.ac.uk

Edward Grefenstette, Oxford University

I am a Franco American computer scientist, working as a research assistant on EPSRC Project EP/I03808X/1 entitled A Unified Model of Compositional and Distributional Semantics: Theory and Applications. I am also lecturing at Hertford College to students taking Oxford's new computer science and philosophy course. From October 2013, I will also be a Fulford Junior Research Fellow at Somerville College.

www.cs.ox.ac.uk

More to be added ...

EUROPE, POLAND

Marcin Murca, University of Warsaw

I am an assistant professor at the Institute of Informatics, University of Warsaw, member of the Algorithms Group (see our blog!).

I work on graph algorithms, approximation algorithms and online algorithms, you can find most of my papers at DBLP or here.

You can find my PhD Thesis here, it contains a rather detailed exposition of the algebraic approach to matching problems in graphs.

duch.mimuw.edu.pl

More to be added ...

ASIA, RUSSIA

Dmitry Efimov, Moscow State University

Dmitry is an expert in promising areas of modern complex and functional analysis; the author of original results. He begins with the systematic study of some classes of analytic functions in the half plane that are analogous to the well known Privalov classes and maximal Privalov classes in the disc. His main results are the following:

1) A new factorization formula and accurate estimates of growth for functions in these classes;

2) The introduction of natural invariant metrics under which the classes form Frecher algebras;

3) A complete description of the linear isometries as well as the bounded and completely bounded subsets in the classes.

mech.math.msu.su

www.kaggle.com

More to be added ...

The

Machine Learning

Salon

Download

Menu