Sciweavers

4080 search results - page 613 / 816
» The rebirth of neural networks
Sort
View
FLAIRS
2007
15 years 9 months ago
Context-Sensitive MTL Networks for Machine Lifelong Learning
Context-sensitive Multiple Task Learning, or csMTL, is presented as a method of inductive transfer that uses a single output neural network and additional contextual inputs for le...
Daniel L. Silver, Ryan Poirier
NECO
2007
115views more  NECO 2007»
15 years 6 months ago
Training Recurrent Networks by Evolino
In recent years, gradient-based LSTM recurrent neural networks (RNNs) solved many previously RNN-unlearnable tasks. Sometimes, however, gradient information is of little use for t...
Jürgen Schmidhuber, Daan Wierstra, Matteo Gag...
NIPS
2003
15 years 8 months ago
Dopamine Modulation in a Basal Ganglio-cortical Network Implements Saliency-based Gating of Working Memory
Dopamine exerts two classes of effect on the sustained neural activity in prefrontal cortex that underlies working memory. Direct release in the cortex increases the contrast of p...
Aaron J. Gruber, Peter Dayan, Boris S. Gutkin, Sar...
NIPS
1994
15 years 8 months 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
GECCO
2006
Springer
147views Optimization» more  GECCO 2006»
15 years 10 months ago
Evolving a real-world vehicle warning system
Many serious automobile accidents could be avoided if drivers were warned of impending crashes before they occur. Creating such warning systems by hand, however, is a difficult an...
Nate Kohl, Kenneth O. Stanley, Risto Miikkulainen,...