Survey
* Your assessment is very important for improving the workof artificial intelligence, which forms the content of this project
* Your assessment is very important for improving the workof artificial intelligence, which forms the content of this project
Biologically Inspired Computation Chris Diorio Computer Science & Engineering University of Washington [email protected] Nature is telling us something... Can add numbers together in nanoseconds Hopelessly beyond the capabilities of brains C. Diorio, 10–8–00 Can understand speech trivially Far ahead of digital computers …and Moore’s law will end 2 Problem: How do we build circuits that learn One approach: Emulate neurobiology Dense arrays of synapses synapse error signal learn signal synapse W21 W22 output W2 j X j j synapse error signal learn signal synapse W11 W12 output W1 j X j j X1 C. Diorio, 10–8–00 input vector X X2 3 Silicon synapses Use the silicon physics itself for learning Local, parallel adaptation Nonvolatile memory Silicon Synapse Transistor Charge Q Sets the Weight -5 10 -6 n+ p floating gate (charge Q) n+ n+ n– electron injection electron tunneling p – substrate source current (A) 10 Q1 -7 Q2 10 Q3 -8 10 Q4 Q5 -9 10 -10 10 -11 10 0 1 2 3 4 5 control-gate–to–source voltage (V) C. Diorio, 10–8–00 4 Silicon synapses can mimic biology Local, autonomous learning Biological Synapses Silicon Synapses synapse source currents (nA) 5 4 3 2 1 0 –10 0 10 20 30 40 50 time (min) Mossy-fiber EPSC amplitudes plotted over time, before and after the induction of LTP. Brief tetanic stimulation was applied at the time indicated. From Barrionuevo et al., J. Neurophysiol. 55:540-550, 1986. C. Diorio, 10–8–00 Synapse transistor source currents plotted over time, before and after we applied a tetanic stimulation of 2×10 5 coincident (row & column) pulses, each of 10 µs duration, at the time indicated. 5 Synaptic circuits can learn complex functions 1 Synapse-based circuit operates on probability distributions Competitive learning Nonvolatile memory 11 transistors 0.35µm CMOS Silicon physics learns “naturally” value (V) 0.8 true means circuit output 0.6 software neural network 0.4 0.2 0 1000 2000 3000 4000 number of training examples Silicon learning circuit versus software neural network Both unmix a mixture of Gaussians Silicon circuit consumes nanowatts Scaleable to many inputs and dimensions C. Diorio, 10–8–00 6 Technology spinoff: Adaptive filters Synapse transistors for signal processing ~100× lower power and ~10× smaller size than digital Mixed-signal FIR filter FIR filter with on-chip learning 16-tap, 7-bits 225MHz, 2.5mW Built and tested in 0.35µm CMOS Adjust synaptic tap weights off-line 64 taps, 10 bits, 200MHz, 25mW In fabrication in 0.35µm CMOS On-line synapse-based LMS C. Diorio, 10–8–00 7 Problem: How to study neural basis of behavior Measure neural signaling in intact animals A. Tritonia and seapen Implant a microcontroller in Tritonia brain Tritonia is a model organism Well studied neurophysiology 500µm neurons; tolerant immune response Work-in-progress Tritonia diomedea MEMS probe tip, amplifier brain visceral cavity memory C. Diorio, 10–8–00 B. Brain with implanted chip: Dorsal view tether battery microcontroller, A/D, cache Images courtesy James Beck & Russell Wyeth 8 An in-flight data recorder for insects An autonomous microcontroller “in-the-loop” Study neural basis of flight control Manduca Sexta or “hawk moth” C. Diorio, 10–8–00 9