Time-series prediction with single integrate-and-fire neuron |
| |
| Affiliation: | 1. Faculty of Industrial Engineering and Management, Technion – Israel Institute of Technology, Haifa, Israel;2. Department of Industrial Engineering, Tel-Aviv University, Tel-Aviv, Israel;1. Department of Computer Science and Information Theory, Budapest University of Technology and Economics, Hungary;2. MTA-ELTE Numerical Analysis and Large Networks Research Group, Hungary;1. Institute of Applied Research, Karlsruhe University of Applied Sciences, Moltkestraße 30, 76133 Karlsruhe, Germany;2. Institute of Applied Materials Reliability of Components and Systems, Karlsruhe Institute of Technology, Engelbert-Arnold-Straße 4, 76131 Karlsruhe, Germany;3. Department of Chemical and Biomolecular Engineering, Korea Advanced Institute of Science and Technology, 291 Daehak-ro, Yuseong-gu, Daejeon 305-701, South Korea;1. Biological Structure, University of Washington Structural Informatics Group, 1959 NE Pacific Street, Box 357420, Seattle, Washington 98195, USA;2. Computer Science and Engineering, University of Washington, Seattle, Washington 98195, USA;3. Biomedical Informatics and Medical Education, University of Washington, Seattle, Washington 98195, USA |
| |
| Abstract: | In this paper, a learning algorithm for a single integrate-and-fire neuron (IFN) is proposed and tested for various applications in which a multilayer perceptron neural network is conventionally used. It is found that a single IFN is sufficient for the applications that require a number of neurons in different hidden layers of a conventional neural network. Several benchmark and real-life problems of classification and time-series prediction have been illustrated. It is observed that the inclusion of some more biological phenomenon in an artificial neural network can make it more powerful. |
| |
| Keywords: | |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
