Zoubin Ghahramani has published a review article in Nature on “Probabilistic machine learning and artificial intelligence” as part of a special issue on Machine Intelligence. This article provides an introduction to the probabilistic framework for designing machines that learn from data, and describes several areas at the frontier of the field, namely, probabilistic programming, Bayesian optimisation, data compression and automatic model discovery.
Archive for year: 2015
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.
Seven new papers from the group are to appear at the 2015 conference on Advances in Neural Information Processing Systems (NIPS 2015), to be held in December in Montreal, Canada.
The list of papers are:
- Statistical Model Criticism using Kernel Two Sample Tests
James Lloyd and Zoubin Ghahramani
- MCMC for Variationally Sparse Gaussian Processes
James Hensman, Alex Matthews, Maurizio Filippone and Zoubin Ghahramani
- Stochastic Expectation Propagation
Yingzhen Li, Jose Miguel Hernandez-Lobato and Richard Turner
- A Linear-Time Particle Gibbs Sampler for Infinite Hidden Markov Models
Nilesh Tripuraneni, Shane Gu, Hong Ge and Zoubin Ghahramani
- Neural Adaptive Sequential Monte Carlo
Shane Gu, Zoubin Ghahramani and Richard Turner
- Parallel Predictive Entropy Search for Batch Global Optimization of Expensive Objective Functions
Amar Shah and Zoubin Ghahramani
- Learning Stationary Time Series using Gaussian Processes with Nonparametric Kernels
Felipe Tobar, Thang Bui and Richard Turner
For the most up to date versions of the papers, visit the authors’ webpages, which may be found through our group members page.
Congratulations to Prof. Zoubin Ghahramani, who has been elected as a Fellow of the Royal Society. His nomination reads:
‘Zoubin Ghahramani is a world leader in the field of machine learning, significantly advancing the state-of-the-art in algorithms that can learn from data. He is known in particular for fundamental contributions to probabilistic modeling and Bayesian nonparametric approaches to machine learning systems, and to the development of approximate variational inference algorithms for scalable learning. He is one of the pioneers of semi-supervised learning methods, active learning algorithms, and sparse Gaussian processes. His development of novel infinite dimensional nonparametric models, such as the infinite latent feature model, has been highly influential.’
See here for the full list of new Fellows.
PhD student Thang D. Bui wins prestigious Google Europe Doctoral Fellowship in Speech Technology. This year 15 fellowships were awarded to new doctoral students across Europe. From the ‘Research at Google’ website:
“In 2009, Google created the PhD Fellowship program to recognize and support outstanding graduate students doing exceptional work in Computer Science and related disciplines. The following year, we launched the program in Europe as the Google European Doctoral Fellowship program. [The recipients of this award] represent the next generation of researchers who will endeavor to solve some of the most interesting challenges in Computer Science. We offer our congratulations, and look forward to their future contributions to the research community with high expectation.”
More information in the link: http://googleresearch.blogspot.co.uk/2015/06/announcing-2015-google-european.html
Congratulations to Richard on winning the Cambridge University Students’ Union Student-Led Teaching Award. This is an award across the entirety of Cambridge with 265 nominations.
The nomination for Richard stated that he is “a brilliant lecturer … able to explain complex ideas in very clear language that students are able to relate to … Perhaps most important, more so than his lecturing style, is his passion for engineering and teaching. Listening to his lectures makes you feel as you yourself are on a voyage of discovery through the field.”
See more at: http://www.eng.cam.ac.uk/news/dr-richard-turner-honoured-teaching-award
Yarin and Mark were awarded a £10,000 prize each by Qualcomm for their innovation proposals titled “Scalable Probabilistic Representation Learning” (Yarin), and “Variational Inference and Kernel Bayes Rule” (Mark). Their award also includes an assignment of a Qualcomm researcher as mentor to facilitate close collaboration and interaction with Qualcomm Corporate Research & Development.
Prof Zoubin Ghahramani speaks on the BBC World Service’s The Forum programme. This 45 minute programme explores the topic of Deep Learning, interviewing Zoubin along with Professor Geoffrey Hinton (Toronto / Google) and Professor Trevor Darrell (Berkeley).
Zoubin also talks to BBC Radio 4 Inside Science about the recent Nature paper by Demis Hassabis and his team at Google DeepMind, in which they teach Deep Reinforcement Learning to play Atari games, and what this implies for AI.
Alex was awarded a £10,000 prize by G-Research for an outstanding PhD with applications to mathematical finance. His thesis, titled “Effective Implementation of Gaussian Process Regression for Machine Learning”, proposed a new framework for the implementation of Gaussian Processes which is currently used by some trading systems.