RSS AI Zone
The neighbors have been at it again.
Stanford develops “Neurogrid [which] simulates a million neurons connected by billions of synapses in real-time, rivaling a supercomputer while consuming a 100,000 times less energy—five watts instead of a megawatt!”
All a one board. Target price: $400.00 USD
This type of processor opens an intirely new avenue for AI.
Example of use: Control of biomechanics with fast computation requirements (for responsiveness)-
“First, a population of neurons collectively represents a time-varying vector through nonlinear encoding and linear decoding.”
Second, alternative linear decodings that transform the vector (linearly or nonlinearly) are used to compute weighted connections from one neural population to the next.
Third, recurrent connections—from a neural population back to itself—realize a transformation that governs the vector’s dynamics.”
For AI these might correspond to:
First, Stimulate neuron(s) with query/input- is a population of neurons (over time)
Second, Finding the best solution… (neural network, Beysian analysis, etc.)
Third, Responding/reacting (text, audio, holographic avatar)
(Fourth, Hello Singularity!?)
