Title :
Stochastic Local Search for direct training of threshold networks
Author :
Mauro Brunato;Roberto Battiti
Author_Institution :
DISI - University of Trento, Italy
fDate :
7/1/2015 12:00:00 AM
Abstract :
This paper investigates Stochastic Local Search (SLS) algorithms for training neural networks with threshold activation functions. and proposes a novel technique, called Binary Learning Machine (BLM). BLM acts by changing individual bits in the binary representation of each weight and picking improving moves.
Keywords :
"Neurons","Annealing","Approximation methods","Training","Benchmark testing","Encoding","Lead"
Conference_Titel :
Neural Networks (IJCNN), 2015 International Joint Conference on
Electronic_ISBN :
2161-4407
DOI :
10.1109/IJCNN.2015.7280770
