Global Sources
EE Times-India
Stay in touch with EE Times India
EE Times-India > FPGAs/PLDs

Neuromorphic systems rival analogue processing

Posted: 23 Apr 2014     Print Version  Bookmark and Share

Keywords:neuromorphic system  DARPA  FPGA  FPAA 

For applications that include cognitive computers, artificial neural networks and neuromorphic systems, there is a resounding demand for these technologies to function on the same level of intelligence as the human brain. One of the agencies spearheading this advancement is the U.S. Defence Advance Research Project (DARPA) with its Neuromorphic Adaptive Plastic Scalable Electronics Human Brain Project. Recently, a team of researchers at Georgia Tech created a roadmap for the development of brain-like neuromorphic systems.

Hasler and George examine an FPGA board

Professor Jennifer Hasler (left) and doctoral candidate Suma George examine an FPGA board. (Source: Rob Felt courtesy of Georgia Tech)

"If you look at the technology we have now, and forward to that which will soon be available, for instance, 11nm processes, then you come to the conclusion that eventually we really could build a human-like cortex in something that could use as little as 50W of power and be small enough to put on your desk," Georgia Tech professor Jennifer Hasler stated.

The roadmap is authored by Hasler and Georgia Tech doctoral candidate Harry Bo Marr, now graduated and working at Raytheon Co. as the technical lead of DARPA's Arrays at Commercial Timescales (ACT) programme and lead electronic warfare digital architect. Hasler and Marr's roadmap also relied upon results obtained by Georgia Tech doctoral candidate Suma George, who experimentally demonstrated, for the first time, that neuromorphic systems based on circuits that tightly model biological principles have clear advantages over other approaches, including typical analogue signal processing techniques.

Hasler's own research emphasises the key role that properly designed analogue processing elements will have on neuromorphic systems, specifically field-programmable analogue arrays (FPAAs) that she and colleagues at Georgia Tech have been perfecting for several years.

FPAAs are similar to field-programmable gate arrays (FPGAs) but include reconfigurable analogue elements. FPAAs are commercially available from Anadigm, but Hasler claimed Georgia Tech's FGAAs "dwarf the programmability and capability of the Anadigm components" by virtue of housing "hundreds of thousands of programmable parameters, enabling them to be used for system-level computing, not just analogue glue logic."

Hasler holds an FPAA board

Hasler holds an FPAA board she is using to emulate biologically based neural networks. (Source: Rob Felt courtesy of Georgia Tech)

1 • 2 Next Page Last Page

Comment on "Neuromorphic systems rival analogue ..."
*  You can enter [0] more charecters.
*Verify code:


Visit Asia Webinars to learn about the latest in technology and get practical design tips.


Go to top             Connect on Facebook      Follow us on Twitter      Follow us on Orkut

Back to Top