Sciweavers

3236 search results - page 403 / 648
» Active kernel learning
Sort
View
NCA
2006
IEEE
15 years 3 months ago
Evolutionary training of hardware realizable multilayer perceptrons
The use of multilayer perceptrons (MLP) with threshold functions (binary step function activations) greatly reduces the complexity of the hardware implementation of neural networks...
Vassilis P. Plagianakos, George D. Magoulas, Micha...
ICML
2008
IEEE
16 years 4 months ago
Modeling interleaved hidden processes
Hidden Markov models assume that observations in time series data stem from some hidden process that can be compactly represented as a Markov chain. We generalize this model by as...
Niels Landwehr
ECTEL
2007
Springer
15 years 9 months ago
The TENCompetence Personal Competence Manager
The European Network for Lifelong Competence Development is an Integrated Project funded by the EU. Its goal is to establish an innovative technical and organizational infrastructu...
Christopher Kew
128
Voted
ICANN
2007
Springer
15 years 9 months ago
Generalized Softmax Networks for Non-linear Component Extraction
Abstract. We develop a probabilistic interpretation of non-linear component extraction in neural networks that activate their hidden units according to a softmaxlike mechanism. On ...
Jörg Lücke, Maneesh Sahani
113
Voted
SIGCSE
2006
ACM
134views Education» more  SIGCSE 2006»
15 years 9 months ago
jFAST: a java finite automata simulator
Visualization and interactivity are valuable active learning techniques that can improve mastery of difficult concepts. In this paper we describe jFAST, an easy-to-use graphical s...
Timothy M. White, Thomas P. Way