Bio-inspired visual memory: a report on the motivation and methodology

Add to your list(s) Download to your calendar using vCal

• Jian Xiong Liu (Imperial College London)
• Monday 21 February 2011, 11:30-12:00
• Level 9 Mahanakorn Lab., EE Dept..

If you have a question about this talk, please contact Grigorios Mingas.

The human memory system is superior for its fast responding speed and huge storage capacity. Although the mechanism behind is still being researched, it is accepted that part of the memory system is dedicated to the processing and storage of visual data. We call it the visual memory. This part of the memory system constructs a so-called ‘mental image’ according to the visual cue presented to the eye and visual scene known already, and passes this mental image to other brain sub-systems for further cognitive services. This project is based on this idea and aims to exploit it to build a novel visual memory system that intelligently understands visual scenes and stores them effectively. Then it should be able to reconstruct visual scenes from given cues – these can be partial information about original stored data. The more details provided, the better the reconstructed images (or mental image) will be. It is a project more connected to AI and machine learning and it is going to be a research into the effective use and innovation of techniques in multiple disciplines, including image compression, super resolution, parallel models of memory system and etc. The presentation will report the details of the motivation behind, my first stage work and my concerns and approaches to solve the problems occurred. I would be happy to talk and discuss with everyone about this bio-inspired project.

This talk is part of the CAS Talks series.

This talk is included in these lists:

• Andrea Picciau's list
• CAS Talks
• Circuits and Systems Group: Internal Seminars
• Level 9 Mahanakorn Lab., EE Dept.

Note that ex-directory lists are not shown.