Novi Quadrianto, Sébastien Bratières, and Zoubin Ghahramani have been awarded an Amazon Web Services (AWS) in Education Research Grant (in the Machine Learning category) in the amount of 10,000 USD in AWS credit for their project on “Large Scale Bayesian Non-parametric Structured Prediction”.
Information about the grant can be found here.
We are pleased to announce the Cambridge-Tübingen PhD fellowships between the University of Cambridge Machine Learning Group and the Max Planck Institute for Intelligent Systems Empirical Inference Department in Tübingen. These fellowships will be co-supervised by Prof. Zoubin Ghahramani in Cambridge and Prof. Bernhard Schoelkopf in Tübingen.
Please see the fellowship webpage and our PhD Admissions FAQ page for more information.
Three new papers from the group are to appear in the Proceeding of Neural Information Processing Systems, 2013, and will be presented at the NIPS conference in Lake Tahoe, USA this December. The papers are:
More information can be found on our publications page.
Richard Turner’s work on developing rich and efficient machine learning methods for audio data with applications ranging from intelligent hearing devices to audio restoration is covered by Wired Magazine and Cambridge Research Horizons Magazine, and is interviewed by Click on the BBC Radio World Service.
Links:
Wired Magazine article: link
Cambridge Research Horizons Magazine article: link
BBC Radio interview recording: link
The 2013 Classic Paper Prize at the International Conference on Machine Learning (ICML) was won by Zoubin Ghahramani and coauthors Xiaojin Zhu and John Lafferty for their 2003 paper “Semi-Supervised Learning Using Gaussian Fields and Harmonic Functions” . The Classic Paper Prize is given to the paper published at ICML 10 years previously which has had the most impact on the field. Semi-supervised learning refers to the problem of combining small amounts of labelled data (i.e. supervised learning) with large amounts of unlabelled data (i.e. unsupervised learning).
This 2003 paper, which has now been cited over 1400 times, developed a simple and highly-scalable graph-based method for semi-supervised classification, and related it to harmonic functions, random walks, electric networks, and spectral graph theory. Graph-based semi-supervised learning has now become a standard approach for combining labelled and unlabelled data in many application domains.
Link to the paper: http://mlg.eng.cam.ac.uk/
Link to the ICML conference: http://icml.cc/2013/
Link to the Machine Learning group website: http://mlg.eng.cam.ac.uk/
Group post-doc Christian Steinruecken radio interviews with The Naked Scientists, an award-winning BBC weekly radio programme delivered by a University-based group focusing on broad topics in science for a general audience. Christian spoke to The Naked Scientists about data compression, some basics of how it works, and its role in the technologies that we employ today.
Learn more about The Naked Scientists and their programme on their webpage.
Information about Christian and his research can be found on his webpage.
The department press release with some excerpts from the interview here.
The original interview can be found here.
You can listen to the interview as an mp3 here.
Eight new papers from the group are to appear in the proceedings of the 30th International Conference on Machine Learning (ICML 2013), to be held in Altanta, Georgia, USA in June. ICML is a leading conference on machine learning. Here are the list of papers with links to the documents:
Abstracts and additional material can be found on our publications page, and links to author webpages can be found on our group members page.
Congratulations to Carl Rasmussen for being awarded the 4th Year Best Lecturer Award in the Engineering department for his teaching in the course “4F13: Machine Learning”. You can find details about the course on our homepage. The excellence in teaching award is voted on by 4th year students in the department.
Richard Turner has been appointed University Lectureship in Computer Vision and Machine Learning. His research programme spans computer perception, signal processing, machine learning, and neuroscience. He’ll strengthen connections between the Computational and Biological Learning Lab, the Machine Intelligence Lab and the Signal Processing Lab.
Richard Turner’s website: http://www.gatsby.ucl.ac.uk/~turner/
Prof. John Cunningham’s article “Neural population dynamics during reaching”, work completed while a Post-Doc in the Machine Learning Group, is published in the journal Nature. From the abstract:
“Most theories of motor cortex have assumed that neural activity represents movement parameters. This view derives from what is known about primary visual cortex, where neural activity represents patterns of light. Yet it is unclear how well the analogy between motor and visual cortex holds. Single-neuron responses in motor cortex are complex, and there is marked disagreement regarding which movement parameters are represented. A better analogy might be with other motor systems, where a common principle is rhythmic neural activity. Here we find that motor cortex responses during reaching contain a brief but strong oscillatory component, something quite unexpected for a non-periodic behaviour. Oscillation amplitude and phase followed naturally from the preparatory state, suggesting a mechanistic role for preparatory neural activity. These results demonstrate an unexpected yet surprisingly simple structure in the population response. This underlying structure explains many of the confusing features of individual neural responses.”
The article: http://www.nature.com/nature/journal/vaop/ncurrent/full/nature11129.html
Press articles: Department; The Atlantic.
Prof. John Cunningham’s website at Washington University in St. Louis: http://cunningham.wustl.edu/