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

30 Sep 2017 evilrobots (Observer)
10 Jun 2017 wedesoft (Master)
9 Jun 2017 mwaibel (Master)
25 May 2017 AI4U (Observer)
25 Feb 2017 steve (Master)
16 Aug 2016 Flanneltron (Journeyer)
27 Jun 2016 Petar.Kormushev (Master)
2 May 2016 motters (Master)
10 Sep 2015 svo (Master)
14 Nov 2014 Sergey Popov (Apprentice)
Share this page