Stochastic neural analog reinforcement calculator

From Wikipedia, the free encyclopedia
Jump to: navigation, search

SNARC (Stochastic Neural Analog Reinforcement Calculator) is a neural net machine designed by Marvin Lee Minsky.[1] George Miller gathered the funding for the project from the Air Force Office of Scientific Research in the summer of 1951. At the time, one of Minsky's graduate students at Princeton, Dean Edmund, volunteered that he was good with electronics and therefore Minsky brought him onto the project.

The machine itself is a randomly connected network of approximately 40 Hebb synapses. These synapses each have a memory that holds the probability that signal comes in one input and another signal will come out of the output. There is a probability knob that goes from 0 to 1 that shows this probability of the signals propagating. If the probability signal gets through, a capacitor remembers this function and engages a "clutch". At this point, the operator will press a button to give reward to the machine. At this point, a large motor starts and there is a chain that goes to all 40 synapse machines, checking if the clutch is engaged or not. As the capacitor can only "remember" for a certain amount of time, the chain only catches the most recent updates of the probabilities.

This machine is considered one of the first pioneering attempts at the field of artificial intelligence, and Minsky is well known for his contributions to what is now the MIT Artificial Intelligence Lab.


  1. ^ Crevier 1993, pp. 34–35 and Russell & Norvig 2003, p. 17