Connectionist Theory Refinement: Genetically Searching the Space of Network Topologies
Journal of Artificial Intelligence Research, Vol 6, (1997), 177-209 An algorithm that learns from a set of examples should ideally be able to exploit the available resources of (a) abundant computing power and (b) domain-specific knowledge to improve its ability to generalize. Connectionist theory-r...
Saved in:
Main Authors | , |
---|---|
Format | Journal Article |
Language | English |
Published |
30.04.1997
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Summary: | Journal of Artificial Intelligence Research, Vol 6, (1997),
177-209 An algorithm that learns from a set of examples should ideally be able to
exploit the available resources of (a) abundant computing power and (b)
domain-specific knowledge to improve its ability to generalize. Connectionist
theory-refinement systems, which use background knowledge to select a neural
network's topology and initial weights, have proven to be effective at
exploiting domain-specific knowledge; however, most do not exploit available
computing power. This weakness occurs because they lack the ability to refine
the topology of the neural networks they produce, thereby limiting
generalization, especially when given impoverished domain theories. We present
the REGENT algorithm which uses (a) domain-specific knowledge to help create an
initial population of knowledge-based neural networks and (b) genetic operators
of crossover and mutation (specifically designed for knowledge-based networks)
to continually search for better network topologies. Experiments on three
real-world domains indicate that our new algorithm is able to significantly
increase generalization compared to a standard connectionist theory-refinement
system, as well as our previous algorithm for growing knowledge-based networks. |
---|---|
DOI: | 10.48550/arxiv.cs/9705102 |