Sciweavers

6039 search results - page 245 / 1208
» The Function Space of an Activity
Sort
View
IJCNN
2008
IEEE
16 years 1 months ago
A comparison of architectural varieties in Radial Basis Function Neural Networks
— Representation of knowledge within a neural model is an active field of research involved with the development of alternative structures, training algorithms, learning modes an...
Mehmet Önder Efe, Cosku Kasnakoglu
DATE
1999
IEEE
74views Hardware» more  DATE 1999»
15 years 11 months ago
FSMD Functional Partitioning for Low Power
Previous work has shown that sizable power reductions can be achieved by shutting down a system's sub-circuits when they are not needed. However, these shutdown techniques fo...
Enoch Hwang, Frank Vahid, Yu-Chin Hsu
AAAI
2008
15 years 9 months ago
Adaptive Importance Sampling with Automatic Model Selection in Value Function Approximation
Off-policy reinforcement learning is aimed at efficiently reusing data samples gathered in the past, which is an essential problem for physically grounded AI as experiments are us...
Hirotaka Hachiya, Takayuki Akiyama, Masashi Sugiya...
ECAI
2010
Springer
15 years 8 months ago
Bayesian Monte Carlo for the Global Optimization of Expensive Functions
In the last decades enormous advances have been made possible for modelling complex (physical) systems by mathematical equations and computer algorithms. To deal with very long run...
Perry Groot, Adriana Birlutiu, Tom Heskes
BC
2007
81views more  BC 2007»
15 years 7 months ago
Cross-intensity functions and the estimate of spike-time jitter
Correlation measures are important tools for the analysis of simultaneously recorded spike trains. A well-known measure with probabilistic interpretation is the cross-intensity fun...
Richard H. R. Hahnloser