Name
Abstract | ||
|---|---|---|
A boosting-based method of learning a feed-forward artificial neural network (ANN) with a single layer of hidden neurons and a single output neuron is presented. Initially, an algorithm called Boostron is described that learns a single-layer perceptron using AdaBoost and decision stumps. It is then extended to learn weights of a neural network with a single hidden layer of linear neurons. Finally, a novel method is introduced to incorporate non-linear activation functions in artificial neural network learning. The proposed method uses series representation to approximate non-linearity of activation functions, learns the coefficients of nonlinear terms by AdaBoost. It adapts the network parameters by a layer-wise iterative traversal of neurons and an appropriate reduction of the problem. A detailed performances comparison of various neural network models learned the proposed methods and those learned using the least mean squared learning (LMS) and the resilient back-propagation (RPROP) is provided in this paper. Several favorable results are reported for 17 synthetic and real-world datasets with different degrees of difficulties for both binary and multi-class problems. |
Year | DOI | Venue |
|---|---|---|
2017 | 10.1016/j.neucom.2017.02.077 | Neurocomputing |
Keywords | Field | DocType |
Artificial neural network,Boostron,Perceptron,Ensemble learning,AdaBoost | AdaBoost,Pattern recognition,Computer science,Probabilistic neural network,Time delay neural network,Types of artificial neural networks,Multilayer perceptron,Boosting (machine learning),Artificial intelligence,Artificial neural network,Rprop,Machine learning | Journal |
Volume | Issue | ISSN |
248 | C | 0925-2312 |
Citations | PageRank | References |
12 | 0.49 | 13 |
Authors | ||
3 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Mubasher Baig | 1 | 12 | 0.49 |
| Mian Awais | 2 | 59 | 11.53 |
| El-Sayed M. El-Alfy | 3 | 187 | 31.43 |