A Comparative Study of Extreme Learning Machine Pruning Based on Detection of Linear Independence
- Resource Type
- Conference
- Authors
- Tavares, L.D.; Saldanha, R.R.; Vieira, D.A.G.; Lisboa, A.C.
- Source
- 2014 IEEE 26th International Conference on Tools with Artificial Intelligence Tools with Artificial Intelligence (ICTAI), 2014 IEEE 26th International Conference on. :63-69 Nov, 2014
- Subject
- Computing and Processing
General Topics for Engineers
Training
Vectors
Neurons
Null space
Testing
Complexity theory
Biological neural networks
Extreme Learning Machines
Pruning
Hidden layer
Linear dependence
- Language
- ISSN
- 1082-3409
2375-0197
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.