Neural Network Exploration Using Optional Experiment Design,

Abstract

We consider the question 'How should one act when the only goal is to learn as much as possible?' Building on the theoretical results of Fedorov (1972) and MacKay (1992), we apply techniques from Optimal Experiment Design (OED) to guide the query/action selection of a neural network learner. We demonstrate that these techniques allow the learner to minimize its generalization error by exploring its domain efficiently and completely. We conclude that, while not a panacea, OED-based query/action has much to offer, especially in domains where its high computational costs can be tolerated.

Keywords

*NEURAL NETS
*EXPERIMENTAL DESIGN
OPTIMIZATION
COMPUTATIONS
HIGH COSTS
LEARNING.

This publication has 0 references indexed in Scilit: