Sacrificial Learning in Nonlinear Perceptrons

Details Sacrificial Learning in Nonlinear Perceptrons Sacrificial Learning in Nonlinear Perceptrons

2000-06-13

arxiv.org/abs/cond-mat/0006206v1

Physics

Condensed Matter

Disordered Systems and Neural Networks

7 pages, 4 figures

Scientific paper

Using the cavity method we consider the learning of noisy teacher-generated examples by a nonlinear student perceptron. For insufficient examples and weak weight decay, the activation distribution of the training examples exhibits a gap for the more difficult examples. This illustrates that the outliers are sacrificed for the overall performance. Simulation shows that the picture of the smooth energy landscape cannot describe the gapped distributions well, implying that a rough energy landscape may complicate the learning process.

Affiliated with

Also associated with

No associations

Rating

Sacrificial Learning in Nonlinear Perceptrons 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 Sacrificial Learning in Nonlinear Perceptrons, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Sacrificial Learning in Nonlinear Perceptrons will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-11901