Loading...
Please wait, while we are loading the content...
Similar Documents
Fast Learning for Big Data Using Dynamic Function
| Content Provider | Scilit |
|---|---|
| Author | Alwajeeh, T. Alharthi, A. F. Rahmat, Romi Fadillah Budiarto, R. |
| Copyright Year | 2017 |
| Description | Journal: Iop Conference Series: Materials Science and Engineering This paper discusses an approach for fast learning in big data. The proposed approach combines momentum factor and training rate, where the momentum is a dynamic function of the training rate in order to avoid overshoot weight to speed up training time of the back propagation neural network engine. The two factors are adjusted dinamically to assure the fast convergence of the training process. Experiments on 2-bit XOR parity problem were conducted using Matlab and a sigmoid function. Experiments results show that the proposed approach signifcantly performs better compare to the standard back propagation neural network in terms of training time. Both, the maximum training time and the minimum training time are significantly faster than the standard algorithm at error threshold of $10^{-5}$. |
| Related Links | http://iopscience.iop.org/article/10.1088/1757-899X/190/1/012015/pdf |
| ISSN | 17578981 |
| e-ISSN | 1757899X |
| DOI | 10.1088/1757-899x/190/1/012015 |
| Journal | Iop Conference Series: Materials Science and Engineering |
| Volume Number | 190 |
| Language | English |
| Publisher | IOP Publishing |
| Publisher Date | 2017-04-19 |
| Access Restriction | Open |
| Subject Keyword | Journal: Iop Conference Series: Materials Science and Engineering Hardware and Architecture Big Data Propagation Neural Network Fast Learning Dynamic Function Training Time Learning for Big |
| Content Type | Text |
| Resource Type | Article |
