Sciweavers

NIPS
1994
14 years 26 days ago
A Connectionist Technique for Accelerated Textual Input: Letting a Network Do the Typing
Each yearpeoplespendahugeamountoftimetyping. Thetextpeopletype typically contains a tremendousamount of redundancy due to predictable word usage patterns and the text's struc...
Dean Pomerleau
NIPS
1994
14 years 26 days ago
Learning Stochastic Perceptrons Under k-Blocking Distributions
We present a statistical method that PAC learns the class of stochastic perceptrons with arbitrary monotonic activation function and weights wi {-1, 0, +1} when the probability d...
Mario Marchand, Saeed Hadjifaradji
NIPS
1994
14 years 26 days ago
Learning with Product Units
Laurens R. Leerink, C. Lee Giles, Bill G. Horne, M...
NIPS
1994
14 years 26 days ago
From Data Distributions to Regularization in Invariant Learning
Ideally pattern recognition machines provide constant output when the inputs are transformed under a group G of desired invariances. These invariances can be achieved by enhancing...
Todd K. Leen
NIPS
1994
14 years 26 days ago
SARDNET: A Self-Organizing Feature Map for Sequences
A self-organizing neural network for sequence classification called SARDNET is described and analyzed experimentally. SARDNET extends the Kohonen Feature Map architecture with act...
Daniel L. James, Risto Miikkulainen
NIPS
1994
14 years 26 days ago
Simplifying Neural Nets by Discovering Flat Minima
Sepp Hochreiter, Jürgen Schmidhuber