Computational Perception Group

home | members | publications | directions | research | presentations | teaching | vacancies | personal


Research in the Computational Perception Group spans the following areas:

  1. machine learning which provides a theoretical framework for learning and making inferences from data in order to make decisions.
  2. computer perception and cognition which builds automatic systems for processing and understanding images, sounds and videos
  3. statistical signal processing which uses techniques from statistics and machine learning to develop new signal processing methods
  4. machine learning for climate science which employs advanced machine learning methods to improve predictions for climate modelling and forecasting to facilitate decision making

Particular current focusses of the group are: deep probabilistic learning, human-like learning, continual learning, k-shot learning, active learning, transfer learning, reinforcement learning, concept learning, probabilistic models, Bayesian statistics, Bayesian neural networks, Gaussian processes, spatio-temporal modelling, approximate inference, scalable and distributed inference, Monte Carlo methods, variational methods, expectation propagation, and Bayesian optimisation. We are also interested in the connection between machine learning and computation in the brain.



opening image

News

28 / 05 / 18 A new draft paper on meta-learning Bayesian inference
11 / 05 / 18 2 papers accepted to ICML2018: Structured Evolution with Compact Architectures for Scalable Policy Optimization and The Mirage of Action-Dependent Baselines in Reinforcement Learning
29 / 01 / 18 3 papers accepted to ICLR2018: Variational Continual Learning, Gaussian Process Behaviour in Wide Deep Neural Networks and Gradient Estimators for Implicit Models
01 / 01 / 18 The Geometry of Random Features accepted to AISTATS2018
23 / 10 / 17 A Unifying Framework for Gaussian Process Pseudo-Point Approximations using Power Expectation Propagation published in JMLR
05 / 09 / 17 Streaming Sparse Gaussian Process Approximations accepted to NIPS2017
05 / 09 / 17 Interpolated Policy Gradient: Merging On-Policy and Off-Policy Gradient Estimation for Deep Reinforcement Learning accepted to NIPS2017
02 / 06 / 17 A new draft paper: Discriminative k-shot learning using probabilistic models
15 / 05 / 17 Two papers [1, 2] accepted to ICML2017
06 / 02 / 17 Q-Prop: Sample-Efficient Policy Gradient with an Off-Policy Critic accepted for oral presentation at ICLR
11 / 17 / 16 The Multivariate Generalised von Mises: Inference and applications accepted for oral presentation at AAAI2017
23 / 11 / 16 Gaussian Processes: From the Basics to the State-of-the-Art, Imperial's ML tutorial series [ slides | video ]
15 / 11 / 16 Awarded a Facebook AI Research Partnership Award (GPU server)
05 / 11 / 16 Advertising a PhD Studentship in one-shot learning using Bayesian deep learning
02 / 11 / 16 Awarded a Google Focussed Award for Reliable and Robust Deep Reinforcement Learning with Shane Gu
30 / 10 / 16 Dr. Cuong Nguyen and James Requeima join the group
26 / 10 / 16 Gaussian Processes for auditory neuroscience, Imperial College London slides
16 / 09 / 16 Machine Learning for Signal Processing keynote presentation [ slides | video ]
12 / 08 / 16 Rényi Divergence Variational Inference accepted to NIPS2016
24 / 04 / 16 Deep Gaussian Processes showing state-of-the-art results on regression accepted to ICML2016
more...
 
This site is powered by FoswikiCopyright © by the contributing authors. All material on this collaboration platform is the property of the contributing authors.
Ideas, requests, problems regarding Foswiki? Send feedback.    Privacy policy