Error Minimized Extreme Learning Machine With Growth of Hidden Nodes and Incremental Learning

One of the open problems in neural network research is how to automatically determine network architectures for given applications. In this brief, we propose a simple and efficient approach to automatically determine the number of hidden nodes in generalized single-hidden-layer feedforward networks...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:IEEE transactions on neural networks Ročník 20; číslo 8; s. 1352 - 1357
Hlavní autoři: Guorui Feng, Guang-Bin Huang, Qingping Lin, Gay, R.
Médium: Journal Article
Jazyk:angličtina
Vydáno: New York, NY IEEE 01.08.2009
Institute of Electrical and Electronics Engineers
Témata:
Algorithm design and analysis
Algorithms
Applied sciences
Artificial Intelligence
Backpropagation algorithms
Classification - methods
Computer science; control theory; systems
Computer Simulation
Connectionism. Neural networks
Convergence
Databases, Factual
Echo state network (ESN)
Errors
Exact sciences and technology
extreme learning machine (ELM)
Feedforward
Feedforward neural networks
feedforward neural networks (FNNs)
growing algorithm
incremental learning
Iterative algorithms
Iterative methods
Learning
Learning - physiology
Machine learning
minimizing error
Networks
Neural networks
Neural Networks (Computer)
Neurons
Neurons - physiology
Pattern Recognition, Automated - methods
Recurrent neural networks
Regression Analysis
sequential learning
Synaptic Transmission - physiology
Time Factors
growing algorithm
Recurrent neural nets
sequential learning
Probabilistic approach
incremental learning
Echo state network (ESN)
Network architecture
feedforward neural networks (FNNs)
minimizing error
Neural network
Artificial intelligence
extreme learning machine (ELM)
ISSN:1045-9227, 1941-0093, 1941-0093
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:One of the open problems in neural network research is how to automatically determine network architectures for given applications. In this brief, we propose a simple and efficient approach to automatically determine the number of hidden nodes in generalized single-hidden-layer feedforward networks (SLFNs) which need not be neural alike. This approach referred to as error minimized extreme learning machine (EM-ELM) can add random hidden nodes to SLFNs one by one or group by group (with varying group size). During the growth of the networks, the output weights are updated incrementally. The convergence of this approach is proved in this brief as well. Simulation results demonstrate and verify that our new approach is much faster than other sequential/incremental/growing algorithms with good generalization performance.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISSN:1045-9227
1941-0093
1941-0093
DOI:10.1109/TNN.2009.2024147