• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.37 no.5
• /
• pp.45-53
• /
• 2000

This paper presents an analysis of the dynamical behavor in the chaotic neuron fabricated using 0.8${\mu}{\textrm}{m}$ single poly CMOS technology. An approximated empirical equation models for the sigmoid output function and chaos generative block of the chaotic neuron are extracted from the measurement data. Then the dynamical responses of the chaotic neuron such as biurcation diagram, frequency responses, Lyapunov exponent, and average firing rate are calculated with numerical analysis. In addition, we construct the chaotic neural networks which are composed of two chaotic neurons with four synapses and obtain bifurcation diagram according to synaptic weight variation. And results of experiments in the single chaotic neuron and chaotic neural networks by two neurons with the $\pm$2.5V power supply and sampling clock frequency of 10KHz are shown and compared with the simulated results.

• Journal of the Institute of Convergence Signal Processing
• /
• v.5 no.1
• /
• pp.32-39
• /
• 2004

Biological neurons generally have chaotic characteristics for permanent or transient period. The effects of chaotic response of biological neuron have not yet been verified by using analytical methods. Even though the transient chaos of neuron could be beneficial to overcoming the local minimum problem, the permanent chaotic response gives adverse effect on optimization problems in general. To solve optimization problems, which are needed in almost all neural network applications such as pattern recognition, identification or prediction, and control, the neuron should have one stable fixed point. In this paper, the dynamic characteristics of the chaotic dynamic neuron and the condition that produces the chaotic response are analyzed, and the convergence conditions are presented.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2002.12a
• /
• pp.199-202
• /
• 2002

신경회로망을 동적 정보처리에 응용하기 위해서는 비대칭 결합 신경회로망에서 생성되는 동적 상태천이에 관한 직관적 이해가 필요하다. 자기결합을 갖고 결합하중치가 비대칭인 순환결합형 신경회로망은 복수 개의 리미트사이클이 기억 가능하다는 것이 알려져 있다. 현재까지 이산시간 모델의 네트워크에 대한 상태천이 해석은 상세하게 이루어져 왔다. 그러나 연속시간 모델에 대한 해석은 네트워크 규모의 증가에 따른 급격한 계산량의 증가 때문에 연구가 그다지 활발하게 이루어지지 않고 있다. 본 논문에서는 각 뉴런이 최근접 뉴런에만 이진화된 결합하중 +1 및 -1로 연결된 연속시간모델 순환결합형 신경회로망의 동적인 상태천이 특성을 해석하여 이산시간 모델에서 기억 가능한 리미트사이클과의 차이점을 분석한다. 또한 연속시간 네트워크 모델에 카오스 신호를 인가하여 리미트사이클간의 천이를 제어할 수 있는 가능성을 분석하여 동적정보처리에 네트워크를 응용할 수 있는 가능성을 검토한다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2001.10a
• /
• pp.605-608
• /
• 2001

다층 신경망의 학습에 쓰이는 오류 역전파 학습은 매우 효과적이지만 학습 속도가 너무 느리고 최적의 은닉충의 뉴런의 수를 결정하는 해답은 아직 없는 실정이다. 또한 가끔은 국부 최소점(Local maxima)에 빠져 학습이 끝내 이루어지지 않는 경우가 있다. 이에 본 논문에서는 이러한 Local maxima 를 효과적으로 탈출 할 수 있는 방법에 대해서 연구해 보았다. 국부 최소점은 연결강도와 전체 오차 사이의 이차원 공간에서 표현할 수 있는데 본 알고리즘은 이러한 연결강도와 오차와의 관계를 인위적으로 변화시켜 결론적으로 Local maxima 를 탈출하게 하는 방법을 소개한다. 본 연구에서 사용된 방법은 네트웍이 학습중에 Local maxima 에 빠졌을 때 은닉층의 뉴런의 수를 추가하여 인위적으로 연결강도 평면의 위상을 변조시킨다. 또한 은닉충의 뉴런의 수를 동적으로 변화 시키면서 최적의 뉴런의 수를 결정할 수 있게 하였다. 위 알고리즘의 성능을 평가하기 위해서 XOR 문제와 $10{\times}8$ 영문폰트와 숫자의 학습에 적용하여 일반적인 역전파 학습과 비교 평가하였다.

• Journal of the Korean Institute of Telematics and Electronics C
• /
• v.36C no.5
• /
• pp.76-85
• /
• 1999

The intuitive understanding of the dynamic pattern generation in asymmetric networks may be useful for developing models of dynamic information processing. In this paper, dynamic behavior of the cyclic connection neural network, in which each neuron is connected only to its nearest neurons with binary synaptic weights of $\pm$ 1, has been investigated. Simulation results show that dynamic behavior of the network can be classified into only three categories: fixed points, limit cycles with basin and limit cycles with no basin. Furthermore, the number and the type of limit cycles generated by the networks have been derived through analytical method. The sufficient conditions for a state vector of $n$-neuron network to produce a limit cycle of $n$- or 2$n$-period are also given. The results show that the estimated number of limit cycles is an exponential function of $n$. On the basis of this study, cyclic connection neural network may be capable of storing a large number of dynamic information.

• Journal of Korea Society of Industrial Information Systems
• /
• v.4 no.1
• /
• pp.68-76
• /
• 1999

The intuitive understanding of the dynamic pattern generation in asymmetric networks may be useful for developing models of dynamic information processing. In this paper, dynamic behavior of the ring connection neural network in which each neuron is only to its nearest neurons with binary synaptic weights of ±1, has been inconnected vestigated Simulation results show that dynamic behavior of the network can be classified into only three categories: fixed points, limit cycles with basin and limit cycles with no basin. Furthermore, the number and the type of limit cycles generated by the networks have been derived through analytical method. The sufficient conditions for a state vector of n-neuron network to produce a limit cycle of n- or 2n-period are also given The results show that the estimated number of limit cycle is an exponential function of n. On the basis of this study, cyclic connection neural network may be capable of storing a large number of dynamic information.

• Proceedings of the Korean Information Science Society Conference
• /
• 2001.10b
• /
• pp.313-315
• /
• 2001

본 논문에서 소개하는 알고리즘을 은닉층의 뉴런의 수를 학습하는 동안 동적으로 변화시켜 역전파 알고리즘의 단점인 Local maxima를 탈출하고 또한 은닉층의 뉴런의 수를 결정하는 과정을 없애기 위해 연구되었다. 본 알고리즘의 성능을 평가하기 위해 두 가지 실험에 적용하였는데 첫번째는 Exclusive-OR 문제이고 두번째는 7$\times$8 한글 자음과 모음의 폰트 학습에 적용하였다. 이 실험의 결과로 네트웍이 local maxima에 빠져드는 확률이 줄어드는 것을 알 수 있었고 학습속도 또한 일반적인 역전파 알고리즘보다 빠른 것으로 증명되었다.

• Proceedings of the Korean Society of Machine Tool Engineers Conference
• /
• 1996.10a
• /
• pp.133-137
• /
• 1996

This paper presents a new approach to the design of neural control system using digital signal processors in order to improve the precision and robustness. Robotic manipulators have bevome increasingly important in the field of flexible automation. High speed and high-precision trajectory tracking arre indispensable capabilities for their versatile application. the need to meet demanding control requirement in increasingly complex dynamical control systems under sygnificant uncertainties leads toward design of implementing real time neural control to provide an enhanced motion control for robotic manipulators. In this control scheme the ntworks intrduced are neural nets with dynamic neurouns whose dynamics are distributed over all the network nodes. The nets are trained by the distributed dynamic are distributed over all the network nodes. The nets are trained by the distributed dynamic back propagation algorithm. The proposed neural network control scheme is simple in structure fast in computation and suitable for implementation of real-time control, Performance of the neural controller is illustrated by simulation and experimental results for a SCAEA robot.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.16 no.2
• /
• pp.179-184
• /
• 2006

An intuitive understanding of the dynamic pattern generation in asymmetric networks may be considered an essential component in developing models for the dynamic information processing. It has been reported that the neural network with cyclic connections generates multiple limit cycles. The dynamics of discrete time network with cyclic connections has been investigated intensively. However, the dynamics of a cyclic connection neural network in continuous-time has not been well-known due to the considerable complexity involved in its calculation. In this paper, the dynamic behavior of a continuous-time cyclic connection neural network, in which each neuron is connected only to its nearest neurons with binary synaptic weights of ${\pm}1$, has been investigated. Furthermore, the dynamics and stability of the network have been analyzed using a piece-wise linear approximation.

• Journal of KIISE:Software and Applications
• /
• v.29 no.6
• /
• pp.386-395
• /
• 2002

In this paper, we suggest dynamic genetic tree-maps(DGTM) using optimal features on recognizing data. The DGTM uses the genetic algorithm about the importance of features rarely considerable on conventional neural networks and introduces GTM(genetic tree-maps) using tree structure according of the priority of features. Hence, we propose the extended formula, DGTM(dynamic GTM) has dynamic functions to separate and merge the neuron of neural network along the similarity of features.