Single-Iteration Learning Algorithm for Feed-Forward Neural Networks

Conference · Sat Jul 31 00:00:00 EDT 1999

OSTI ID:6257

Barhen, J; Cogswell, R; Protopopescu, V

A new methodology for neural learning is presented, whereby only a single iteration is required to train a feed-forward network with near-optimal results. To this aim, a virtual input layer is added to the multi-layer architecture. The virtual input layer is connected to the nominal input layer by a specird nonlinear transfer function, and to the fwst hidden layer by regular (linear) synapses. A sequence of alternating direction singular vrdue decompositions is then used to determine precisely the inter-layer synaptic weights. This algorithm exploits the known separability of the linear (inter-layer propagation) and nonlinear (neuron activation) aspects of information &ansfer within a neural network.

• Research Organization: Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States); Oak Ridge, TN
• Sponsoring Organization: USDOE Office of Science (SC)
• DOE Contract Number: AC05-96OR22464
• OSTI ID: 6257
• Report Number(s): ORNL/CP-102700; KC 04 01 03 0; ON: DE00006257
• Resource Relation: Conference: 5th Conference of Information Systems Analysis and Synthesis (ISAS '99)/ 3rd Conference of Systemics Cybernetics, and Informatics (SCI '99), Orlando, FL, July 31-August 4, 1999
• Country of Publication: United States
• Language: English

Related Subjects

99 MATHEMATICS
COMPUTERS
INFORMATION SCIENCE
MANAGEMENT
LAW
MISCELLANEOUS
Learning
Algorithms
Neural Networks