Spaun (Semantic Pointer Architecture Unified Network)

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

Spaun ("Semantic Pointer Architecture Unified Network") is a cognitive architecture pioneered by Chris Eliasmith of the University of Waterloo Centre for Theoretical Neuroscience.[1] It consists of 2.5 million simulated neurons organized into subsystems that resemble specific brain regions, such as the prefrontal cortex, basal ganglia, and thalamus. It can recognize numbers, remember them, figure out numeric sequences, and even write them down with a robotic arm. [2][3] It is implemented using Nengo.


  1. ^ "Spaun: Chris Eliasmith on how to build a brain". University of Waterloo. 6 March 2013. Retrieved 17 May 2016.
  2. ^ "Meet Spaun, The Most Complex Simulated Brain Ever". Retrieved May 17, 2016.
  3. ^ Eliasmith, C., Stewart T. C., Choo X., Bekolay T., DeWolf T., Tang Y., Rasmussen, D. (2012). A large-scale model of the functioning brain. Science. Vol. 338 no. 6111 pp. 1202-1205. DOI: 10.1126/science.1225266.