The BICI Lab, initially known as the BICV (Biologically-Inspired Computer Vision) Group, was founded out of the work of Anil Bharath and Jeffrey Ng around 2002, with funding from RCUK and EPSRC. It is hosted within the Department of Bioengineering at Imperial College, London, where it beneifits from strong interactions within a very multidisciplinary Department. The recent change from BICV to BICI reflects a broadening of remit to algorithm design: from purely visual data to data from other sources. For more about exactly what we do, see About.

In a nutshell, the members of the lab design algorithms to analyse data. What is a “biologically-inspired” approach?  There are many facets to algorithm design (power consumption, architecture), but our inspiration is largely fed by the way that biological neurons encode visual data. For example, two interesting and relevant phenomena of biological sensory processing are: a) the complex neurons of V1 and b) some non-linear effects that are part of population encoding. Some of these principles are to be found – either explicity or implicity – within deep networks.

At a systems level, we have also used approaches that are  similar to those now appearing in deep learning, such as denoising convolutional auto-encoders [Bharath & Ng, 2005].  The spin-out Cortexica Vision Systems (acquired by Zebra Technologies Ltd in 2019) used this technology to provide commercial visual search using cloud-based GPUs as early as 2010. You can find out more about the original technology here. Cortexica is now an independent company, and so you should contact them directly to learn more about what they do, and for access to this technology.