Punyaphol Horata

Learn More
The output weights computing of extreme learning machine (ELM) encounters two problems, the computational and outlier robustness problems. The computational problem occurs when the hidden layer output matrix is a not full column rank matrix or an ill-conditioned matrix because of randomly generated input weights and biases. An existing solution to this(More)
Most feed-forward artificial neural network training algorithms for classification problems are based on an iterative steepest descent technique. Their well-known drawback is slow convergence. A fast solution is an Extreme Learning Machine (ELM) computing the Moore-Penrose inverse using SVD. However, the most significant training time is pseudo-inverse(More)
Feature extraction plays an essential role in hand written character recognition because of its effect on the capability of classifiers. This paper presents a framework for investigating and comparing the recognition ability of two classifiers: Deep-Learning Feedforward-Backpropagation Neural Network (DFBNN) and Extreme Learning Machine (ELM). Three data(More)
Unsupervised Extreme Learning Machine (US-ELM) is the one type of neural network which modified from Extreme Learning Machine (ELM) for handle the clustering problem. Nevertheless, US-ELM has problem with nonfulfillment of solution due to K-Mean algorithm was used to cluster which made the accuracy of solution was unstable when training many times. In this(More)
Circular Extreme Learning Machine (C-ELM) is an extension of Extreme Learning Machine. Its power is mapping both linear and circular separation boundaries. However, C-ELM uses the random determination of the input weights and hidden biases, which may lead to local optimal. This paper proposes a hybrid learning algorithms based on the C-ELM and the(More)
The most difficult problem with the extreme learning machine is the selection of the hidden nodes size. The proper number of hidden nodes is predefined through a trial and error approach. The convex incremental extreme learning machine (CI-ELM) has been proposed to tackle this problem. CI-ELM is an incremental constructive neural network with universal(More)
For learning in big datasets, the classification performance of ELM might be low due to input samples are not extracted features properly. To address this problem, the hierarchical extreme learning machine (H-ELM) framework was proposed based on the hierarchical learning architecture of multilayer perceptron. H-ELM composes of two parts; the first is the(More)
Multi-instance learning (MIL) is a classification approach for classifying on a collection of instances which each group is represented as a bag. The main task of MIL is to learn from labels and features of instances to produce a model to predict a label of a testing bag. Traditional MIL algorithms were proposed to address the MIL problem, but most of the(More)
Extreme Learning Machine (ELM) model which learn very faster than other neural networks model but the solution was not suitable as expected since the randomness of the input weights and biases may cause to the nonfulfillment of solution. Flower Pollination Extreme Learning Machine (FP-ELM) model that it was merged by ELM and Flower Pollination Algorithm(More)
  • 1