If you want to design robots able to interact to the real world in a useful way, you will eventually bump into the problem of implementing robust object recognition, when by robust I mean able to recognize objects irrespective of (or at least able to tolerate variation in..) distance from the object, its orientation, illumination conditions, etc.
June 15, 2012|
February 21, 2012|
A very interesting article just came out on on Mercury News with an interview to"HP Labs Director Prith Banerjee mentioning the latest HP Lab strategies and Cog Ex Machina, the software platform developed by HP Labs in collaboration with the Boston University Neuromorphics Lab. Full disclosure... I direct that lab! So yes, I may be biased... but read on. This gives some hints of what applications can come out of this platform. And we hope this is just the beginning!
Read the rest of this entry »
August 25, 2011|
One of the main goals of Neurdon, since its very beginnings, was to educate readers to tell apart fiction from reality. Nowadays, big companies are diving (or dive-bombing) in the field of neural computing with hyperbolic claims of being able to simulate biological brains, from feline to humans. One of such a claim comes, again, from IBM. This is the truth behind what IBM calls "cognitive computer". Read the rest of this entry »
August 9, 2011|
This brief essay, originated by the work on the Neuromorphics Lab in the DARPA SyNAPSE project, describes our early effort in the study of alternative computing schemes that will make use of massive memristive-based devices coupled with low-power CMOS processes to efficiently compute neural activation and learning in novel computing devices. The answer was to couple fuzzy inference with dense memristive memory. This combination can provide extensive power and silicon real estate savings while maintaining a high degree of accuracy in the resulting precision of the computations. Read the rest of this entry »