347 search results - page 60 / 70 » esann 2007 |
ESANN
2007
13 years 9 months ago
2007
Local algorithms for non-linear dimensionality reduction [1], [2], [3], [4], [5] and semi-supervised learning algorithms [6], [7] use spectral decomposition based on a nearest neig...
ESANN
2007
13 years 9 months ago
2007
Training recurrent neural networks is hard. Recently it has however been discovered that it is possible to just construct a random recurrent topology, and only train a single linea...
ESANN
2007
13 years 9 months ago
2007
This paper presents our Recurrent Control Neural Network (RCNN), which is a model-based approach for a data-efficient modelling and control of reinforcement learning problems in di...
ESANN
2007
13 years 9 months ago
2007
This paper proposes a novel nonlinear transient computation device described as the LTCM that uses the chaotic attractor provided by the Lorenz system of equations to perform patte...
ESANN
2007
13 years 9 months ago
2007
Mixtures of probabilistic principal component analyzers model high-dimensional nonlinear data by combining local linear models. Each mixture component is specifically designed to...