Extreme learning machine adapted to noise based on optimization algorithms. (March 2020)

• Record Type: Journal Article
• Authors: Vásquez, A; Mora, M; Salazar, E; Gelvez, E
• Is Part Of: Journal of physics. Volume 1514(2020)
• Publication Date: 2020-03
• Subjects: Physics -- Congresses; 530.5
• DOI: 10.1088/1742-6596/1514/1/012006
• Languages: English
• ISSNs: 1742-6588

Abstract

Abstract: The extreme learning machine for neural networks of feedforward of a single hidden layer randomly assigns the weights of entry and analytically determines the weights the output by means the Moore-Penrose inverse, this algorithm tends to provide an extremely fast learning speed preserving the adjustment levels achieved by classifiers such as multilayer perception and support vector machine. However, the Moore-Penrose inverse loses precision when using data with additive noise in training. That is why in this paper a method to robustness of extreme learning machine to additive noise proposed. The method consists in computing the weights of the output layer using non-linear optimization algorithms without restrictions. Tests are performed with the gradient descent optimization algorithm and with the Levenberg-Marquardt algorithm. From the implementation it is observed that through the use of these algorithms, smaller errors are achieved than those obtained with the Moore-Penrose inverse.