Neural Network Hardware Update

Posted 15 Feb 2007 at 23:47 UTC by steve Share This

A Technology Review article describes Stanford's Brains in Silicon project, which is attempting to replicate neurons in hardware with more detail and accuracy that previous attempts. Stanford's Neurocore chip is a 256x256 array of neurons that duplicate several types of biological neurons found in the cortex. They also emulate the chemical and physical properties of neurons such as protein pores and ion channels. Neurocore chips are combined into 4x4 grids to form NeuroGrid boards. IBM's Blue Gene super computer took 1 hour, 20 minutes to simulate one second of visual cortex activity. Kwabena Boahen and other Stanford researchers hope to see a Neurogrid-based computer perform visual cortex simulations in real time soon. For more on hardware-based artificial neural networks, see our previous articles.

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