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] It is a randomly connected network of Hebb synapses.

It was implemented by Minsky while he was a student, in hardware using vacuum tubes, and was possibly the first artificial self-learning machine.


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


  • Crevier 1993
  • Russell Norvig 2003
  • Riello Rusconi 2011 Unimanual SNARC Effect: Hand Matters. Front Psychol, 2, 372.
  • CyberneticZoo1053
  • Minsky interview videos on SNARC: part 1, 2