ilteris kaplan blog

connectionism and neural networks

November 16, 2005

I was reading and trying to clear it in my mind of all those concepts of connectionism, behavior-based systems, neural networks, cognitive synthetic psychology and I am not having an easy time.


connectionism is an approach which models behavior phenomena as the emergent processes of interconnected network of units [which are neurons that are connected as synapses at this point].

Neural Networks is the main form of connectionist Model. And what it works from Wikipedia:

  1. Any given mental state can be described as a (N)-dimensional vector of numeric activation values over neural units in a network.
  2. Memory is created by modifying the strength of the connections between neural units. The connection strengths, or “weights”, are generally represented as a (N×N)-dimensional matrix.

so rethinking what I am trying to do with the final project, I was going to create a system which strengths the connections in itself, ok in what way? What could be better in my scenario? What could my agent do better in time?

It could map the topography of the area it is exploring maybe.

Written by Ilteris Kaplan who still lives and works in New York. Twitter