.png){kind=icon}
.png){kind=icon}
Return
Autoencoding With a Classifier System
.png){kind=icon}
OA
AI
DOI：10.1109/TEVC.2021.3079320.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Autoencoders are data-specific compression algorithms learned automatically from examples. The predominant approach has been to construct single large global models that cover the domain. However, training and evaluating models of increasing size comes at the price of additional time and computational cost. Conditional computation, sparsity, and model pruning techniques can reduce these costs while maintaining performance. Learning classifier systems (LCSs) are a framework for adaptively subdividing input spaces into an ensemble of simpler local approximations that together cover the domain. LCS perform conditional computation through the use of a population of individual gating/guarding components, each associated with a local approximation. This article explores the use of an LCS to adaptively decompose the input domain into a collection of small autoencoders, where local solutions of different complexity may emerge. In addition to the benefits in convergence time and computational cost, it is shown possible to reduce the code size as well as the resulting decoder computational cost when compared with the global model equivalent.
Keywords:
Neural networks
Statistics
Sociology
Neurons
Computational modeling
Decoding
Computational efficiency
Autoencoder
evolutionary algorithm (EA)
learning classifier system (LCS)
neural network
self-adaptation
stochastic gradient descent
XCSF
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
12
Papers:
1.8K
Citations:
2.4W