Sciweavers

98 search results - page 12 / 20
» Training Recurrent Networks by Evolino
Sort
View
ICDAR
2011
IEEE
13 years 11 months ago
Co-training for Handwritten Word Recognition
—To cope with the tremendous variations of writing styles encountered between different individuals, unconstrained automatic handwriting recognition systems need to be trained on...
Volkmar Frinken, Andreas Fischer, Horst Bunke, Ali...
NIPS
1993
15 years 1 months ago
Credit Assignment through Time: Alternatives to Backpropagation
Learning to recognize or predict sequences using long-term context has many applications. However, practical and theoretical problems are found in training recurrent neural networ...
Yoshua Bengio, Paolo Frasconi
NECO
2011
14 years 6 months ago
Mechanisms That Modulate the Transfer of Spiking Correlations
Correlations between neuronal spike trains impact network dynamics and population coding. Overlapping afferent populations and correlations between presynaptic spike trains intro...
Robert Rosenbaum, Kresimir Josic
EAAI
2006
123views more  EAAI 2006»
14 years 12 months ago
Imitation learning with spiking neural networks and real-world devices
This article is about a new approach in robotic learning systems. It provides a method to use a real-world device that operates in real-time, controlled through a simulated recurr...
Harald Burgsteiner
KDD
2004
ACM
166views Data Mining» more  KDD 2004»
16 years 7 days ago
Predicting prostate cancer recurrence via maximizing the concordance index
In order to effectively use machine learning algorithms, e.g., neural networks, for the analysis of survival data, the correct treatment of censored data is crucial. The concordan...
Lian Yan, David Verbel, Olivier Saidi