Sciweavers

257 search results - page 44 / 52
» neco 2006
Sort
View
NECO
2002
78views more  NECO 2002»
13 years 7 months ago
Local Overfitting Control via Leverages
We present a novel approach to dealing with overfitting in black-box models. It is based on the leverages of the samples, i.e. on the influence that each observation has on the pa...
Gaétan Monari, Gérard Dreyfus
NECO
2002
53views more  NECO 2002»
13 years 7 months ago
Information-Geometric Measure for Neural Spikes
The present study introduces information-geometricmeasures to analyze neural ring patterns by taking not only the secondorder but also higher-order interactions among neurons into...
Hiroyuki Nakahara, Shun-ichi Amari
NECO
1998
121views more  NECO 1998»
13 years 7 months ago
Nonlinear Time-Series Prediction with Missing and Noisy Data
We derive solutions for the problem of missing and noisy data in nonlinear timeseries prediction from a probabilistic point of view. We discuss different approximations to the so...
Volker Tresp, Reimar Hofmann
NECO
1998
119views more  NECO 1998»
13 years 7 months ago
Density Estimation by Mixture Models with Smoothing Priors
In the statistical approach for self-organizing maps (SOMs), learning is regarded as an estimation algorithm for a Gaussian mixture model with a Gaussian smoothing prior on the ce...
Akio Utsugi
NECO
2002
106views more  NECO 2002»
13 years 7 months ago
Learning Nonregular Languages: A Comparison of Simple Recurrent Networks and LSTM
In response to Rodriguez' recent article (2001) we compare the performance of simple recurrent nets and "Long Short-Term Memory" (LSTM) recurrent nets on context-fr...
Jürgen Schmidhuber, Felix A. Gers, Douglas Ec...