Sciweavers

171 search results - page 2 / 35
» Solution Methods for a New Class of Simple Model Neurons
Sort
View
DATE
2003
IEEE
114views Hardware» more  DATE 2003»
13 years 10 months ago
Extraction of Piecewise-Linear Analog Circuit Models from Trained Neural Networks Using Hidden Neuron Clustering
This paper presents a new technique for automatically creating analog circuit models. The method extracts - from trained neural networks - piecewise linear models expressing the l...
Simona Doboli, Gaurav Gothoskar, Alex Doboli
ICANN
2009
Springer
13 years 10 months ago
Constrained Learning Vector Quantization or Relaxed k-Separability
Neural networks and other sophisticated machine learning algorithms frequently miss simple solutions that can be discovered by a more constrained learning methods. Transition from ...
Marek Grochowski, Wlodzislaw Duch
EVOW
2001
Springer
13 years 9 months ago
Evolution of Spiking Neural Controllers for Autonomous Vision-Based Robots
Abstract. We describe a set of preliminary experiments to evolve spiking neural controllers for a vision-based mobile robot. All the evolutionary experiments are carried out on phy...
Dario Floreano, Claudio Mattiussi
IJCNN
2000
IEEE
13 years 9 months ago
A New Method for Tracking Modulations in Tonal Music in Audio Data Format
Cq-profiles are 12-dimensional vectors, each component referring to a pitch class. They can be employed to represent keys. Cq-profiles are calculated with the constant Q filter...
Hendrik Purwins, Benjamin Blankertz, Klaus Obermay...
SIAMCO
2008
121views more  SIAMCO 2008»
13 years 5 months ago
A Direct Solution Method for Stochastic Impulse Control Problems of One-dimensional Diffusions
We consider stochastic impulse control problems where the process is driven by one-dimensional diffusions. Impulse control problems are widely applied to financial engineering and...
Masahiko Egami