9_NeuromorphicComputing3080 Mario Quispe

9_NeuromorphicComputing3080 Mario Quispe - 8 The challenge...

Info iconThis preview shows pages 1–11. Sign up to view the full content.

View Full Document Right Arrow Icon
Neuromorphic Computing Mario Quispe ECE 3080 April 12, 2011
Background image of page 1

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
2 We Will Be Looking at… Basic concept of neuromorphic computing Incentive behind neuromorphic computing Facilitation of technology Architecture of Neurogrid Neuromorphic vision chips Complementary Oxide Memristor Barriers preventing advancement
Background image of page 2
3 First… Neuron - axon and dendrite Synapses: Chemical/Electrical Inhibitory synapse response Excitatory synapse response
Background image of page 3

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
4 What is neuromorphic computing? How information is transferred in the brain: Neurons Ion Channel Neural Networks Parallel neural networks
Background image of page 4
5 Advantages Modern integrated circuits cannot downsize anymore Less power with neuromorphic computing 200,000 W - 80 teraflops 10 W – 10^16 complex operations/s
Background image of page 5

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
6 Neurogrid Simulation of biological brain Analog computation Digital communication
Background image of page 6
7 Vision Chips Simulation of retina in silicon chip How visual field is interpreted to the brain Emulation of the retina
Background image of page 7

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Background image of page 8
Background image of page 9

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Background image of page 10
Background image of page 11
This is the end of the preview. Sign up to access the rest of the document.

Unformatted text preview: 8 The challenge Retina cell 0.5 mm thickness 0.5 grams 0.1 W 9 Using memristors Able to emulate excitatory/inhibitory synapse Change in voltage rapid recovery of resistance Maintain resistance 10 Work in progress Todays computers rely on serial connections Relatively new branch for computing 11 Sources Boahen, Kwabena. Making a computer that works like the brain. 30 July 2008. Online video clip. Youtube. Accessed April 4, 2011. Koch, Christof, Mathur, Bimal Neurmorphic vision chips. IEEE Xplore May 1996. Neurogrid. Brains in Silicon. 2006. Stanford University. <http://www.stanford.edu/group/brainsinsilicon/index.html> Mead, Carver Neuromorphic Electronic Systems. IEEE October 1990. Calley, W. Laws, Doolittle, Alan W. and Henderson, Walter. COM Technology Facilitating both Inhibitory and Excitatory Synapses for Potential Neuromorphic Computing Applications. IEEE December 2009....
View Full Document

This note was uploaded on 08/23/2011 for the course ECE 3080 taught by Professor Staff during the Spring '08 term at Georgia Institute of Technology.

Page1 / 11

9_NeuromorphicComputing3080 Mario Quispe - 8 The challenge...

This preview shows document pages 1 - 11. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online