Metamorphosis Networks: An Alternative to Constructive Models
Lists
Only you see this
Abstract
Given a set of training examples, determining the appropriate number of free parameters is a challenging problem. Constructive learning algorithms attempt to solve this problem automatically by adding hidden units, and therefore free parameters, during learning. We explore an alternative class of algorithms--called metamorphosis algorithms--in which the number of units is fixed, but the number of free parameters gradually increases during learning. The architecture we investigate is composed of RBF units on a lattice, which imposes flexible constraints on the parameters of the network. Virtues of this approach include variable subset selection, robust parameter selection, multiresolution processing, and interpolation of sparse training data.
BibTeX
@inproceedings{bonnlander1992metamorphosis,
author = {Brian Bonnlander and Michael C. Mozer},
title = {{Metamorphosis Networks: An Alternative to Constructive Models}},
booktitle = {Advances in Neural Information Processing Systems},
year = {1992},
url = {https://openreview.net/forum?id=HJ-RK8-dbB},
}Loading related content...