269 search results - page 18 / 54 » A Minimax Method for Learning Functional Networks |
NCA
2006
IEEE
13 years 7 months ago
2006
IEEE
The use of multilayer perceptrons (MLP) with threshold functions (binary step function activations) greatly reduces the complexity of the hardware implementation of neural networks...
FOCI
2007
IEEE
14 years 1 months ago
2007
IEEE
— A learning machine is called singular if its Fisher information matrix is singular. Almost all learning machines used in information processing are singular, for example, layer...
ICML
2007
IEEE
14 years 8 months ago
2007
IEEE
We present a method for parameter learning in relational Bayesian networks (RBNs). Our approach consists of compiling the RBN model into a computation graph for the likelihood fun...
EMNLP
2010
13 years 5 months ago
2010
In contrast with the booming increase of internet data, state-of-art QA (question answering) systems, otherwise, concerned data from specific domains or resources such as search e...
ICANN
2003
Springer
14 years 23 days ago
2003
Springer
Abstract. An abstract recurrent neural network trained by an unsupervised method is applied to the kinematic control of a robot arm. The network is a novel extension of the Neural ...