Sciweavers

28 search results - page 1 / 6
» Opposite Transfer Functions and Backpropagation Through Time
Sort
View
104
Voted
FOCI
2007
IEEE
15 years 7 months ago
Opposite Transfer Functions and Backpropagation Through Time
— Backpropagation through time is a very popular discrete-time recurrent neural network training algorithm. However, the computational time associated with the learning process t...
Mario Ventresca, Hamid R. Tizhoosh
93
Voted
IJCNN
2006
IEEE
15 years 7 months ago
Improving the Convergence of Backpropagation by Opposite Transfer Functions
—The backpropagation algorithm is a very popular approach to learning in feed-forward multi-layer perceptron networks. However, in many scenarios the time required to adequately ...
Mario Ventresca, Hamid R. Tizhoosh
98
Voted
ENTCS
2008
130views more  ENTCS 2008»
15 years 1 months ago
The SPARTA Pseudonym and Authorization System
This paper deals with privacy-preserving (pseudonymized) access to a service resource. In such a scenario, two opposite needs seem to emerge. On one side, the service provider may...
Giuseppe Bianchi, M. Bonola, Vincenzo Falletta, Fr...
92
Voted
NIPS
1990
15 years 2 months ago
Back Propagation is Sensitive to Initial Conditions
This paper explores the effect of initial weight selection on feed-forward networks learning simple functions with the back-propagation technique. We first demonstrate, through th...
John F. Kolen, Jordan B. Pollack
TNN
2010
234views Management» more  TNN 2010»
14 years 7 months ago
Novel maximum-margin training algorithms for supervised neural networks
This paper proposes three novel training methods, two of them based on the back-propagation approach and a third one based on information theory for Multilayer Perceptron (MLP) bin...
Oswaldo Ludwig, Urbano Nunes