Sciweavers

46 search results - page 6 / 10
» nips 1996
Sort
View
NIPS
1996
14 years 11 months ago
Adaptively Growing Hierarchical Mixtures of Experts
We propose a novelapproach to automaticallygrowing and pruning Hierarchical Mixtures of Experts. The constructive algorithm proposed here enables large hierarchies consisting of s...
Jürgen Fritsch, Michael Finke, Alex Waibel
NIPS
1996
14 years 11 months ago
Why did TD-Gammon Work?
Although TD-Gammon is one of the major successes in machine learning, it has not led to similar impressive breakthroughs in temporal difference learning for other applications or ...
Jordan B. Pollack, Alan D. Blair
NIPS
1996
14 years 11 months ago
Solving the Ill-Conditioning in Neural Network Learning
Abstract. In this paper we investigate the feed-forward learning problem. The well-known ill-conditioning which is present in most feed-forward learning problems is shown to be the...
P. Patrick van der Smagt, Gerd Hirzinger
NIPS
1996
14 years 11 months ago
Reconstructing Stimulus Velocity from Neuronal Responses in Area MT
We employed a white-noise velocity signal to study the dynamics of the response of single neurons in the cortical area MT to visual motion. Responses were quantified using reverse...
Wyeth Bair, James R. Cavanaugh, J. Anthony Movshon
NIPS
1996
14 years 11 months ago
Are Hopfield Networks Faster than Conventional Computers?
It is shown that conventional computers can be exponentially faster than planar Hopfield networks: although there are planar Hopfield networks that take exponential time to conver...
Ian Parberry, Hung-Li Tseng