Active Learning Based on Single-Hidden Layer Feed-Forward Neural Network

Prediction of rainfall data by using Feed Forward Neural Network (FFNN) model is proposed. FFNN is a class of neural network which has three layers for processing. In time series prediction, including in case of rainfall data, the input layer is the past values of the same series up to certain lag and the output layer is the current value. Beside a few lagged times, the seasonal pattern also considered as an important aspect of choosing the potential input. The autocorrelation function and partial autocorrelation function patterns are used as aid of selecting the input. In the second layer called hidden layer, the logistic sigmoid is used as activation function because of the monotonic and differentiable. Processing is done by the weighted summing of the input variables and transfer process in the hidden layer. Backpropagation algorithm is applied in the training process. Some gradient based optimization methods are used to obtain the connection weights of FFNN model. The prediction is the output resulting of the process in the last layer. In each optimization method, the looping process is performed several times in order to get the most suitable result in various composition of separating data. The best one is chosen by the least mean square error (MSE) criteria. The least of in-sample and out-sample predictions from the repeating results been the base of choosing the best optimization method. In this study, the model is applied in the ten-daily rainfall data of ZOM 136 Cokrotulung Klaten. Simulation results give a consecution that the more complex architecture is not guarantee the better prediction.

Download Full-text

Analisis Pengenalan Bendera Negara Rumpun Melayu Menggunakan Metode Feed Forward Neural Network

Jurnal Teknologi dan Informasi ◽

10.34010/jati.v10i2.2702 ◽

2020 ◽

Vol 10 (2) ◽

pp. 144-152

Author(s):

H Santoso ◽

D Murdianto

Keyword(s):

Neural Network ◽

Artificial Intelligence ◽

Learning Rate ◽

Feed Forward Neural Network ◽

Feed Forward ◽

Brunei Darussalam ◽

Hidden Layer

Telah dilakukan analisis pada sistem pengenalan gambar empat buah bendera negara rumpun melayu secara digital. Negara tersebut adalah Indonesia, Malaysia, Singapura, dan Brunei Darussalam. Tujuan dari penelitian ini adalah sebagai bentuk langkah awal dalam melatih sistem Artificial Intelligence (Kecerdasan Buatan) dalam membedakan empat buah negara rumpun melayu berdasarkan warna dan motif bendera pada sebuah peta digital. Proses analisis dan pelatihan pengenalan bendera tersebut menggunakan metode Feed Forward Neural Network (FFNN). Hasilnya menunjukkan bahwa penggunaan 4 buah Hidden Layer, serta penggunaan Learning Rate 0,5 memberikan kemampuan pengenalan citra bendera secara tepat dengan persentase akurasi rata-rata mencapai 74,15%.

Download Full-text

Musical pitch estimation using a supervised single hidden layer feed-forward neural network

Expert Systems with Applications ◽

10.1016/j.eswa.2012.07.063 ◽

2013 ◽

Vol 40 (2) ◽

pp. 575-589 ◽

Cited By ~ 6

Author(s):

Pat Taweewat ◽

Chai Wutiwiwatchai

Keyword(s):

Neural Network ◽

Feed Forward Neural Network ◽

Pitch Estimation ◽

Feed Forward ◽

Musical Pitch ◽

Hidden Layer

Download Full-text

A Modified Particle Swarm Optimization with Neural Network via Euclidean Distance

International Journal of Recent Contributions from Engineering Science & IT (iJES) ◽

10.3991/ijes.v6i1.8080 ◽

2018 ◽

Vol 6 (1) ◽

pp. 4

Author(s):

Asia L. Jabar ◽

Tarik A. Rashid

Keyword(s):

Neural Network ◽

Particle Swarm Optimization ◽

Euclidean Distance ◽

Particle Swarm ◽

Classification Problem ◽

Feed Forward Neural Network ◽

Distance Method ◽

Swarm Optimization ◽

Feed Forward ◽

Hidden Layer

<p>In this paper, a new modified model of Feed Forward Neural Network with Particle Swarm Optimization via using Euclidean Distance method (FNNPSOED) is used to better handle a classification problem of the employee’s behavior. The Particle Swarm Optimization (PSO) as a natural inspired algorithm is used to support the Feed Forward Neural Network (FNN) with one hidden layer in obtaining the optimum weights and biases using different hidden layer neurons numbers. The key reason of using ED with PSO is to take the distance between each two-feature value then use this distance as a random number in the velocity equation for the velocity value in the PSO algorithm. The FNNPSOED is used to classify employees’ behavior using 29 unique features. The FNNPSOED is evaluated against the Feed Forward Neural Network with Particle Swarm Optimization (FNNPSO). The FNNPSOED produced satisfactory results.</p>

Download Full-text

On Training Efficiency and Computational Costs of a Feed Forward Neural Network: A Review

Computational Intelligence and Neuroscience ◽

10.1155/2015/818243 ◽

2015 ◽

Vol 2015 ◽

pp. 1-13 ◽

Cited By ~ 25

Author(s):

Antonino Laudani ◽

Gabriele Maria Lozito ◽

Francesco Riganti Fulginei ◽

Alessandro Salvini

Keyword(s):

Neural Network ◽

Activation Function ◽

General Purpose ◽

Feed Forward Neural Network ◽

Embedded Computing ◽

Feed Forward ◽

Computational Costs ◽

Computing Environments ◽

Hidden Layer ◽

Network Mapping

A comprehensive review on the problem of choosing a suitable activation function for the hidden layer of a feed forward neural network has been widely investigated. Since the nonlinear component of a neural network is the main contributor to the network mapping capabilities, the different choices that may lead to enhanced performances, in terms of training, generalization, or computational costs, are analyzed, both in general-purpose and in embedded computing environments. Finally, a strategy to convert a network configuration between different activation functions without altering the network mapping capabilities will be presented.

Download Full-text