A Comparison between Seven Heuristic Methods to Estimate the Number of Hidden Layer Neurons in a Multi Layer Perceptron Neural Network
Journal: International Journal of Advanced Trends in Computer Science and Engineering (IJATCSE) (Vol.10, No. 2)Publication Date: 2021-04-09
Authors : Mutasem Sh. Alkhasawneh;
Page : 955-963
Keywords : Pruning Neurons; Neurons Number; Hidden layer; MLP stability; MLP performance; Heuristic Methods.;
Abstract
Multilayer Perceptron Neural Network (MLPNNs) constructs of input, at least one hidden and output layer. Number of the neurons in the hidden layer affects the NNs performance. It also consider difficult task to overcome. This research, aims to exanimate the performance of seven heuristic methods that have been used to estimate the neurons numbers in the hidden layer. The effectiveness of these methods was verified using a six of benchmark datasets. The number of hidden layer neurons that selected by each heuristic method for every data set was used to train the MLP. The results demonstrate that the number of hidden neurons selected by each method provides different accuracy and stability compared with other methods. The number of neurons selected by Hush method for ine data set was 26 neurons. It's achieved the best accuracy with 99.90%and lowest accuracy achieved by Sheela method with 67.51% using 4 neurons. Using 22 neurons with 97.97% accuracy Ke, J method received the best result for Ionosphere data set. While the lowest accuracy was 96.95% with 5 neurons achieved by Kayama method.For Iris data set with 8 neurons achieved 97.19 as best accuracy achieved by Hush method. For the same data set the lowest results were 92.33 % using 3 neurons obtained by using Kayama method. For WBC data set 96.40% the best accuracy achieved using Sheela and Kaastra methods using 4 and 7neurons, while Kanellopoulos method achieved the lowest accuracy 94.18% with 7neurons. For Glass dataset, 87.15% was the best obtained accuracy using 18 neurons Hush method and using Wang method 82.27 % with 6 neurons was the lowest accuracy. Finally for PID 75.31% accuracy achieved by Kayama method with 3 neurons, where Kanellopoulos method obtained 72.17% through using 24 neurons.
Other Latest Articles
- Knowledge Representation of Highly Dynamic Ontologies Using Defeasible Logic
- Ripeness Level Classification of Banana Fruit Based on Hue Saturate Value (HSV) Color Space Using K-Nearest Neighbor Algorithm
- Steady State Analysis and Impact of Benban Solar Park on The Egyptian Transmission System
- Numerical Investigation of Newtonian Fluid Flow around Sharp & Rounded Corner Rectangular Obstruction
- Challenges of Accent and vowels for Sindhi Speech Recognition System
Last modified: 2021-04-12 15:44:32