Browsing by Author "Wei, JD"

Now showing 1 - 4 of 4

A neural network model of hysteresis
(1996)
Wei, JD
;
Sun, CT
;
交大名義發表
;
資訊工程學系
;
National Chiao Tung University
Hysteresis is an effect of memory, which is frequently observed in the realm of nature. The purpose of this paper is trying to understand more of it, such that we may achieve better performance from the systems which are hysteresis-embedded. A hypothesis-based neural network model is offered in this paper. We name it the Synchronous Delay Network (SDN) model. It can be realized as a feed-forward neural network. We also discuss the possible applications in this paper.
Constructing hysteretic memory in neural networks
(2000-08-01)
Wei, JD
;
Sun, CT
;
資訊工程學系
;
Department of Computer Science
Hysteresis is a unique type of dynamic, which contains an important property, rate-independent memory. In addition to other memory-related studies such as time delay neural networks, recurrent networks, and reinforcement learning, rate-independent memory deserves further attention owing to its potential applications. In this work, we attempt to define hysteretic memory (rate-independent memory) and examine whether or not it could be modeled in neural networks. Our analysis results demonstrate that other memory-related mechanisms are not hysteresis systems. A novel neural cell, referred to herein as the propulsive neural unit, is then proposed. The proposed cell is based on a notion related the submemory pool, which accumulates the stimulus and ultimately assists neural networks to achieve model hysteresis. In addition to training by backpropagation, a combination of such cells can simulate given hysteresis trajectories.
Large simulation of hysteresis systems using a piecewise polynomial function
(2002-07-01)
Wei, JD
;
Sun, CT
;
資訊工程學系
;
Department of Computer Science
Hysteresis is a memory effect frequently observed in physical research. The output of a hysteresis system is independent of input speed. This property, known as rate independence, significantly distinguishes hysteresis from short-term memory effects. This work conducts a numerical simulation to demonstrate that conventional models with short-term memories cannot properly simulate hysteresis trajectories. Subsequently, a novel model is developed to contribute to the field of system modeling. Experimental results confirm that the proposed model can model hysteresis behavior precisely.
Varying appearance speed problem in system modeling and a solution via rate independent memory
(2002-05-01)
Wei, JD
;
Sun, CT
;
資訊工程學系
;
Department of Computer Science
Conventional system models such as the finite impulse response (FIR.) model, autoregressive external input (ARX) model, time delay neural network (TDNN), and recurrent neural network (RNN) depend on short-term memory when modeling a discrete time system. However, short-term memory can be inefficient with a varying appearance speed of I/O data. This inefficiency is referred to herein as the Varying Appearance Speed Problem (VASP) and demonstrated by analyzing impulse and frequency responses. Simulation results indicate that the varying appearance speed leads to asymmetrical cycles. Unable to prevent the memory effect from extensively disturbing the next output cycle, conventional models simulate the systems inaccurately. A solution using rate independent memory is then proposed. Only concerned with the previous extreme inputs, rate independent memory differs from short-term memory and potentially prevents a system model from the impact of varying appearance speeds. To demonstrate the VASP and verify the proposed model, this study conducts three experiments, i.e. (a) learning random step trajectories of circular and trefoil shapes, (b) modeling the relationship between the economic leading and coincident indexes, (c) simulating the connection between the ground-water level and land subsidence. In contrast to conventional models, the model presented here performs better in terms of mean square errors.