CBP Neural Net Implemented in Hardware

Posted 21 May 2003 at 16:23 UTC by steve Share This

NASA has applied for a patent on a novel method of implementing a cascade back-propagation (CBP) neural network in VLSI hardware. Previously, even hardware-based neural networks required software-based learning algorithms. By implementing CBP learning in hardware along with the neural net, the time required to train the network is greatly reduced. NASA is calling the new system On-Chip Cascade Back Propagation Learning. Details are available in a NASA Tech Brief (PDF format, free registration required).

See more of the latest robot news!

Recent blogs

28 Nov 2015 mwaibel (Master)
25 Nov 2015 shimniok (Journeyer)
6 Nov 2015 wedesoft (Master)
26 Oct 2015 steve (Master)
20 Oct 2015 Flanneltron (Journeyer)
10 Sep 2015 svo (Master)
9 Aug 2015 Petar.Kormushev (Master)
6 May 2015 spirit (Journeyer)
14 Nov 2014 Sergey Popov (Apprentice)
3 Jul 2014 jmhenry (Journeyer)
Share this page