Sciweavers

265 search results - page 21 / 53
» On the Computational Power of Neural Nets
Sort
View
GECCO
2005
Springer
204views Optimization» more  GECCO 2005»
15 years 5 months ago
Modeling systems with internal state using evolino
Existing Recurrent Neural Networks (RNNs) are limited in their ability to model dynamical systems with nonlinearities and hidden internal states. Here we use our general framework...
Daan Wierstra, Faustino J. Gomez, Jürgen Schm...
ICANN
2005
Springer
15 years 5 months ago
On Variations of Power Iteration
The power iteration is a classical method for computing the eigenvector associated with the largest eigenvalue of a matrix. The subspace iteration is an extension of the power iter...
Seungjin Choi
ACMACE
2006
ACM
15 years 5 months ago
Motivated reinforcement learning for non-player characters in persistent computer game worlds
Massively multiplayer online computer games are played in complex, persistent virtual worlds. Over time, the landscape of these worlds evolves and changes as players create and pe...
Kathryn Elizabeth Merrick, Mary Lou Maher
GECCO
2004
Springer
169views Optimization» more  GECCO 2004»
15 years 5 months ago
Genetic Programming Neural Networks as a Bioinformatics Tool for Human Genetics
The identification of genes that influence the risk of common, complex diseases primarily through interactions with other genes and environmental factors remains a statistical and ...
Marylyn D. Ritchie, Christopher S. Coffey, Jason H...
ISPA
2004
Springer
15 years 5 months ago
Towards Correct Distributed Simulation of High-Level Petri Nets with Fine-Grained Partitioning
Abstract. Powerful grid and cluster computers allow efficient distributed simulation. Optimistic simulation techniques have been developed which allow for more parallelism in the l...
Michael Knoke, Felix Kühling, Armin Zimmerman...