Sciweavers

9730 search results - page 306 / 1946
» Relating models of backtracking
Sort
View
148
Voted
ESANN
2001
15 years 6 months ago
Penalized least squares, model selection, convex hull classes and neural nets
We develop improved risk bounds for function estimation with models such as single hidden layer neural nets, using a penalized least squares criterion to select the size of the mod...
Gerald H. L. Cheang, Andrew R. Barron
153
Voted
NIPS
2004
15 years 6 months ago
Spike-timing Dependent Plasticity and Mutual Information Maximization for a Spiking Neuron Model
We derive an optimal learning rule in the sense of mutual information maximization for a spiking neuron model. Under the assumption of small fluctuations of the input, we find a s...
Taro Toyoizumi, Jean-Pascal Pfister, Kazuyuki Aiha...
144
Voted
NIPS
2001
15 years 6 months ago
Modeling Temporal Structure in Classical Conditioning
The Temporal Coding Hypothesis of Miller and colleagues [7] suggests that animals integrate related temporal patterns of stimuli into single memory representations. We formalize t...
Aaron C. Courville, David S. Touretzky
PARMA
2004
162views Database» more  PARMA 2004»
15 years 6 months ago
UML-based Conceptual Modeling of Pattern-Bases
The concept of pattern, meant as an interesting knowledge artifact extracted from data, is considered to be a an effective answer to the advanced analysis requirements emerging in ...
Stefano Rizzi
143
Voted
GG
2008
Springer
15 years 6 months ago
Graph Transformation for Topology Modelling
In this paper we present meta-rules to express an infinite class of semantically related graph transformation rules in the context of pure topological modelling with G-maps. Our p...
Mathieu Poudret, Agnès Arnould, Jean-Paul C...