Sciweavers

2210 search results - page 39 / 442
» Information complexity of neural networks
Sort
View
TNN
2008
114views more  TNN 2008»
14 years 11 months ago
Relevance-Based Feature Extraction for Hyperspectral Images
Abstract--Hyperspectral imagery affords researchers all discriminating details needed for fine delineation of many material classes. This delineation is essential for scientific re...
Michael J. Mendenhall, Erzsébet Meré...
IJCAI
1997
15 years 1 months ago
Extracting Propositions from Trained Neural Networks
This paper presents an algorithm for extract­ ing propositions from trained neural networks. The algorithm is a decompositional approach which can be applied to any neural networ...
Hiroshi Tsukimoto
GECCO
2005
Springer
155views Optimization» more  GECCO 2005»
15 years 5 months ago
Co-evolving recurrent neurons learn deep memory POMDPs
Recurrent neural networks are theoretically capable of learning complex temporal sequences, but training them through gradient-descent is too slow and unstable for practical use i...
Faustino J. Gomez, Jürgen Schmidhuber
ISNN
2005
Springer
15 years 5 months ago
Internet Traffic Prediction by W-Boost: Classification and Regression
Abstract. Internet traffic prediction plays a fundamental role in network design, management, control, and optimization. The self-similar and non-linear nature of network traffic m...
Hanghang Tong, Chongrong Li, Jingrui He, Yang Chen
85
Voted
NIPS
1993
15 years 1 months ago
Structural and Behavioral Evolution of Recurrent Networks
This paper introduces GNARL, an evolutionary program which induces recurrent neural networks that are structurally unconstrained. In contrast to constructive and destructive algor...
Gregory M. Saunders, Peter J. Angeline, Jordan B. ...