Sciweavers

4366 search results - page 236 / 874
» Learning and Smoothed Analysis
Sort
View
IWANN
2005
Springer
15 years 9 months ago
Real-Time Spiking Neural Network: An Adaptive Cerebellar Model
Abstract. A spiking neural network modeling the cerebellum is presented. The model, consisting of more than 2000 conductance-based neurons and more than 50 000 synapses, runs in re...
Christian Boucheny, Richard R. Carrillo, Eduardo R...
KDD
2008
ACM
172views Data Mining» more  KDD 2008»
16 years 4 months ago
Structured metric learning for high dimensional problems
The success of popular algorithms such as k-means clustering or nearest neighbor searches depend on the assumption that the underlying distance functions reflect domain-specific n...
Jason V. Davis, Inderjit S. Dhillon
ICML
2008
IEEE
16 years 5 months ago
A worst-case comparison between temporal difference and residual gradient with linear function approximation
Residual gradient (RG) was proposed as an alternative to TD(0) for policy evaluation when function approximation is used, but there exists little formal analysis comparing them ex...
Lihong Li
ALT
2005
Springer
16 years 1 months ago
Gold-Style and Query Learning Under Various Constraints on the Target Class
In language learning, strong relationships between Gold-style models and query models have recently been observed: in some quite general setting Gold-style learners can be replaced...
Sanjay Jain, Steffen Lange, Sandra Zilles
IJCNN
2008
IEEE
15 years 10 months ago
Learning to select relevant perspective in a dynamic environment
— When an agent observes its environment, there are two important characteristics of the perceived information. One is the relevance of information and the other is redundancy. T...
Zhihui Luo, David A. Bell, Barry McCollum, Qingxia...