Anil Anthony Bharath is Professor of Biologically-Inspired Computation & Inference in the Department of Bioengineering at Imperial. He holds a degree in Electrical & Electronic Engineering from UCL, and a PhD from Imperial College.
He has worked on convolution-based architectures for visual processing since the mid 1990s. His current research is focussed on the use of deep networks for inference, and his group has recently published reviews on deep reinforcement learning and generative adversarial networks, as well as original research in these two fields.
Anil has published in the fields of pattern recognition, machine learning and signal processing, and has extensive experience in computer vision. In 1998, he demonstrated the first application of steerable filters (convolution-based architectures, with feedback) to shape detection. Later contributions included the use of Bayesian marginalisation in very early-stage computer vision, focus-of-attention methods, and custom-designed wavelet transforms to analyse images in a scalable manner.
In 2002, Dr. Bharath initiated the Basic Technology Project "Reverse Engineering Human Visual Processes", which created a blueprint for a scalable subset of processes in the human visual system, particularly of visual area V1.
In 2008, Dr. Bharath spun out the company Cortexica Vision Systems, which applies simplified models of the behaviour of visual neurons to visual search. Cortexica was acquired by Zebra Technologies in 2019. See http://www.bici-lab.org/ for more details, as well as a brief discussion on how these models are related to modern convolutional neural networks.
Anil’s research publications can be found at the tab above, or on Google Scholar
et al., 2013, A Novel Method for Quantifying Spatial Correlations Between Patterns of Atherosclerosis and Hemodynamic Factors, Journal of Biomechanical Engineering-Transactions of the ASME, Vol:135, ISSN:0148-0731
Ip HMD, Drakakis EM, Bharath AA, 2008, Synthesis of nonseparable 3-D spatiotemporal bandpass filters on analog networks, IEEE Transactions on Circuits and Systems. Part 1: Regular Papers, Vol:55, ISSN:1549-8328, Pages:298-310
Ip HMD, Drakakis EM, Bharath AA, 2008, On Analog Networks and Mixed-Domain Spatio-Temporal Frequency Response, IEEE Transactions on Circuits and Systems. Part 1: Regular Papers, Vol:55, ISSN:1549-8328, Pages:284-297