Back to Search
Start Over
Building feedforward neural networks with random weights for large scale datasets.
- Source :
-
Expert Systems with Applications . Sep2018, Vol. 106, p233-243. 11p. - Publication Year :
- 2018
-
Abstract
- With the explosive growth in size of datasets, it becomes more significant to develop effective learning schemes for neural networks to deal with large scale data modelling. This paper proposes an iterative approximate Newton-type learning algorithm to build neural networks with random weights (NNRWs) for problem solving, where the whole training samples are divided into some small subsets under certain assumptions, and each subset is employed to construct a local learner model for integrating a unified classifier. The convergence of the output weights of the unified learner model is given. Experimental results on UCI datasets with comparisons demonstrate that the proposed algorithm is promising for large scale datasets. [ABSTRACT FROM AUTHOR]
Details
- Language :
- English
- ISSN :
- 09574174
- Volume :
- 106
- Database :
- Academic Search Index
- Journal :
- Expert Systems with Applications
- Publication Type :
- Academic Journal
- Accession number :
- 129608224
- Full Text :
- https://doi.org/10.1016/j.eswa.2018.04.007