NIPS
1993
13 years 6 months ago
1993
We consider the problem of how the CNS learns to control dynamics of a mechanical system. By using a paradigm where a subject's hand interacts with a virtual mechanical envir...
NIPS
1993
13 years 6 months ago
1993
The non-linear complexities of neural networks make network solutions difficult to understand. Sanger's contribution analysis is here extended to the analysis of networks aut...
NIPS
1993
13 years 6 months ago
1993
The game of Go has a high branching factor that defeats the tree search approach used in computer chess, and long-range spatiotemporal interactions that make position evaluation e...
NIPS
1993
13 years 6 months ago
1993
NIPS
1993
13 years 6 months ago
1993
This paper introduces GNARL, an evolutionary program which induces recurrent neural networks that are structurally unconstrained. In contrast to constructive and destructive algor...
NIPS
1993
13 years 6 months ago
1993
We propose a learning algorithm for a variable memory length Markov process. Human communication, whether given as text, handwriting, or speech, has multi characteristic time scal...
NIPS
1993
13 years 6 months ago
1993
Parti-game is a new algorithm for learning feasible trajectories to goal regions in high dimensionalcontinuousstate-spaces. In high dimensions it is essential that learningdoes not...
NIPS
1993
13 years 6 months ago
1993
NIPS
1993
13 years 6 months ago
1993
We present a new algorithm for eliminating excess parameters and improving network generalization after supervised training. The method, \Principal Components Pruning (PCP)",...
NIPS
1993
13 years 6 months ago
1993
Stochastic optimization algorithms typically use learning rate schedules that behave asymptotically as (t) = 0=t. The ensemble dynamics (Leen and Moody, 1993) for such algorithms ...