Time Series Forecasting With Orthogonal Endocrine Neural Network Based on Postsynaptic PotentialsSource: Journal of Dynamic Systems, Measurement, and Control:;2017:;volume( 139 ):;issue: 004::page 41006Author:Milovanović, Miroslav
,
Antić, Dragan
,
Milojković, Marko
,
Nikolić, Saša S.
,
Spasić, Miodrag
,
Perić, Staniša
DOI: 10.1115/1.4035090Publisher: The American Society of Mechanical Engineers (ASME)
Abstract: This paper presents a new type of endocrine neural network (ENN). ENN utilizes artificial glands which enable the network to be adaptive to external disturbances. Sensitivity is controlled by the hormone decay rate and the value of the sensitivity parameter. The network presented in this paper is improved by making the sensitivity parameter self-tuning and implementing orthogonal activation functions inside the network structure. Automatic tuning is performed on the basis of the biological principle of postsynaptic potentials by implementing inhibitory and excitatory glands inside the standard backpropagation learning algorithm of developed orthogonal ENN. These additional network functionalities enable extra sensitivity to external conditions and an additional network feature of activation sharpening. The network was tested on real-time series of experimental data with a purpose to forecast exchange rate of the three widely used international currencies.
|
Show full item record
| contributor author | Milovanović, Miroslav | |
| contributor author | Antić, Dragan | |
| contributor author | Milojković, Marko | |
| contributor author | Nikolić, Saša S. | |
| contributor author | Spasić, Miodrag | |
| contributor author | Perić, Staniša | |
| date accessioned | 2017-11-25T07:20:43Z | |
| date available | 2017-11-25T07:20:43Z | |
| date copyright | 2017/7/2 | |
| date issued | 2017 | |
| identifier issn | 0022-0434 | |
| identifier other | ds_139_04_041006.pdf | |
| identifier uri | http://138.201.223.254:8080/yetl1/handle/yetl/4236612 | |
| description abstract | This paper presents a new type of endocrine neural network (ENN). ENN utilizes artificial glands which enable the network to be adaptive to external disturbances. Sensitivity is controlled by the hormone decay rate and the value of the sensitivity parameter. The network presented in this paper is improved by making the sensitivity parameter self-tuning and implementing orthogonal activation functions inside the network structure. Automatic tuning is performed on the basis of the biological principle of postsynaptic potentials by implementing inhibitory and excitatory glands inside the standard backpropagation learning algorithm of developed orthogonal ENN. These additional network functionalities enable extra sensitivity to external conditions and an additional network feature of activation sharpening. The network was tested on real-time series of experimental data with a purpose to forecast exchange rate of the three widely used international currencies. | |
| publisher | The American Society of Mechanical Engineers (ASME) | |
| title | Time Series Forecasting With Orthogonal Endocrine Neural Network Based on Postsynaptic Potentials | |
| type | Journal Paper | |
| journal volume | 139 | |
| journal issue | 4 | |
| journal title | Journal of Dynamic Systems, Measurement, and Control | |
| identifier doi | 10.1115/1.4035090 | |
| journal fristpage | 41006 | |
| journal lastpage | 041006-9 | |
| tree | Journal of Dynamic Systems, Measurement, and Control:;2017:;volume( 139 ):;issue: 004 | |
| contenttype | Fulltext |