Title :
A Comparative Study of Extreme Learning Machine Pruning Based on Detection of Linear Independence
Author :
Tavares, L.D. ; Saldanha, R.R. ; Vieira, D.A.G. ; Lisboa, A.C.
Author_Institution :
Grad. Program in Electr. Eng., Fed. Univ. of Minas Gerais, Belo Horizonte, Brazil
Abstract :
Extreme Learning Machine (ELM) is gaining fairly popularity in training neural networks, due to its simplicity and speed. However, the number of neurons in the hidden layer is still an open problem. This paper proposes a method for pruning the hidden layer neurons based on the linear combination of the hidden layer weights and the input data and compare four methods of detecting linear dependence between vectors.
Keywords :
learning (artificial intelligence); neural nets; ELM; extreme learning machine pruning; hidden layer weights; linear independence detection; neural networks; training; Biological neural networks; Complexity theory; Neurons; Null space; Testing; Training; Vectors; Extreme Learning Machines; Hidden layer; Linear dependence; Pruning;
Conference_Titel :
Tools with Artificial Intelligence (ICTAI), 2014 IEEE 26th International Conference on
Conference_Location :
Limassol
DOI :
10.1109/ICTAI.2014.20
