Reconfigurable Spin Switch
- Summary
- Researchers at Purdue University have developed technology for a hardware neural network implementation using a spin switch (SS) as its basic building block. This allows neural networks to be constructed with purely passive interconnections without intervening clocks or amplifiers. The weights for the neural network are conveniently adjusted through analog voltages that can be stored in a non-volatile manner in an underlying CMOS layer using a floating gate low drop out voltage regulator. The operation of a multilayer SS neural network designed for character recognition is demonstrated using a standard simulation model based on coupled Lanadau-Lifshitz-Gilbert equations, one for each magnet in the network.
- Technology Benefits
- Requires less power than current methods Unit size is relatively small
- Technology Application
- Computer networks
- Detailed Technology Description
- Supriyo DattaPurdue Electrical and Computer Engineering
- Countries
- United States
- Application No.
- None
- *Abstract
-
- *Background
- Nanomagnets driven by spin currents provide a natural implementation for a neuron and a synapse. Currents allow convenient summation of multiple inputs, while the magnet provides the threshold function. Spin switch is a recently proposed device based on established technology with a transistor-like gain and input-output isolation.
- *IP Issue Date
- None
- *IP Type
- Utility
- *Stage of Development
- Proof of concept
- *Web Links
- Purdue Office of Technology CommercializationPurdueInnovation and EntrepreneurshipSupriyo DattaPurdue Electrical and Computer Engineering
- Country/Region
- USA
For more information, please click Here
