Learning by dilution in a Neural Network

Details Learning by dilution in a Neural Network Learning by dilution in a Neural Network

1996-11-18

arxiv.org/abs/cond-mat/9611130v1

Physics

Condensed Matter

Disordered Systems and Neural Networks

LaTeX, 15 pages incl. figures

Scientific paper

10.1088/0305-4470/30/22/014

A perceptron with N random weights can store of the order of N patterns by removing a fraction of the weights without changing their strengths. The critical storage capacity as a function of the concentration of the remaining bonds for random outputs and for outputs given by a teacher perceptron is calculated. A simple Hebb-like dilution algorithm is presented which in the teacher case reaches the optimal generalization ability.

Affiliated with

Also associated with

No associations

Rating

Learning by dilution in a Neural Network does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with Learning by dilution in a Neural Network, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Learning by dilution in a Neural Network will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-484886