Dr. Richard E. Turner

University Lecturer in Computer Vision and Machine Learning,
Computational and Biological Learning Lab
University of Cambridge, Department of Engineering
ret26-at-cam.ac.uk

My research lies at the interface between computer perception (which builds artificial systems for understanding images, sounds and videos), neuroscience (which tries to understand the brain) and machine-learning (which provides a theoretical framework for learning from data). The goal is to develop systems that solve important problems, drawing inspiration from the brain. For example, figuring out how many sound sources there are in an acoustic scene and what the individual contributions from each source are. There are medical and engineering applications of this work, such as in cochlear implants for the deaf. Importantly, the behaviour of these systems can also be compared to neural processing in the brain in order to better understand what the brain is doing.

I have openings for PhD students in my group. Reading material can be found here.

Areas of Research and Projects:

Machine Perception

Statistical models for audio and video

Theoretical understanding of learning algorithms as probabilistic inference

Machine Vision

Learning invariances from natural images for object recognition

Statistical models for images

Machine Hearing

Synthesis of audio textures for computer games and artificial environments

Source separation

Neuroscience

Auditory processing as probabilistic inference

Neural implementations of approximate inference

Machine Learning

Approximate inference for time-series

Circular statistics and time-series

Signal Processing

Unifying signal processing and machine learning

Removing signal distortions using machine learning & signal processing

Current Highlights:

Started University Lectureship in Computer Vision and Machine Learning at the University of Cambridge, UK in the Department of Engineering on September 1st, 2012.
An introductory tutorial on Gaussian Processes presented at the Sheffield Gaussian Process Summer School June, 2013
New Conference Paper: Probabilistic amplitude and frequency demodulation. Awarded spotlight presentation at NIPS 2011.
New Journal Paper: Demodulation as Probabilistic Inference. There is an associated webpage with code and a listing of related publications here.
Completed an EPSRC Postdoctoral Fellowship Grant at the Interface for the Life Sciences. I divided my time between the CBL Lab in Cambridge with Zoubin Ghahramani and at the Lab for Computer Vision, NYU with Eero Simoncelli.
A finished version of my PhD Thesis, Statistical Models for Natural Sounds is now ready. There are also a number of related audio demonstrations.

Papers, talks, and teaching

Workshops and meetings organised

Essential Tools for scientists meeting. A weekly meeting to discuss topics essential to scientific life, which are not formally taught. Things like unit testing, acceleration of code, reference management, version control, time-management, latex, presentation style, etc.
Advanced probabilistic techniques workshop A two hour lecture on a probabilistic method (loopy BP, EP, DBNs, DPs and SMCMS) followed by coding up the method on a toy problem in a pair
Beyond Simple Cells (BSC) workshop Computational modelers of visual cortex meet the physiologists whose data they try and model.

Sounds

Audio demonstrations

CV

Here's my cv.

Personal

Contact details
Computational and Biological Learning Lab
University of Cambridge Engineering Department
Trumpington Street, Cambridge, CB2 1PZ, UK
ret26-at-cam.ac.uk

last updated 11 June 2013