• Tunnel and Underground Space
• /
• v.6 no.4
• /
• pp.316-325
• /
• 1996

A new accelerated neural network adopting modified sigmoid function was developed and applied to estimate engineering properties of rock from insufficient geological data. Developed network was tested on the well-known XOR and character recognition problems to verify the validity of the algorithms. Both learning speed and recognition rate were improved. Test learn on the Lee and Sterling's problems showed that learning time was reduced from tens of hours to a few minutes, while the output pattern was almost the same as other studies. Application to the various case studies showed exact coincidence with original data or measured results.

• Journal of information and communication convergence engineering
• /
• v.1 no.3
• /
• pp.157-162
• /
• 2003

We propose a learning method for improving the performance of the backpropagation algorithm. The proposed method is using a fuzzy logic system for automatic tuning of the learning rate of each weight. Instead of choosing a fixed learning rate, the fuzzy logic system is used to dynamically adjust the learning rate. The inputs of fuzzy logic system are delta and delta bar, and the output of fuzzy logic system is the learning rate. In order to verify the effectiveness of the proposed method, we performed simulations on the XOR problem, character classification, and function approximation. The results show that the proposed method considerably improves the performance compared to the general backpropagation, the backpropagation with momentum, and the Jacobs'delta-bar-delta algorithm.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.29B no.9
• /
• pp.68-75
• /
• 1992

In this paper the back-propagation algorithm through omitting redundant learning has been proposed to improve learning speed. The proposed algorithm has been applied to XOR, Parity check and pattern recognition of hand-written numbers. The decrease of the number of patterns to be learned has been confirmed as learning proceeds even in early learning stage. The learning speed in pattern recognition of hand-written numbers is improved more than 2 times in various cases of hidden neuron numbers. It is observed that the improvement of learning speed becomes better as the number of patterns and the number of hidden numbers increase. The recognition rate of the proposed algorithm is nearly the same as that conventional method.

• Journal of Korea Society of Industrial Information Systems
• /
• v.7 no.3
• /
• pp.62-67
• /
• 2002

From the view point of VLSI implementation, a new teaming algorithm suited for network with quantized connection weights is desired. This paper presents a new teaming algorithm for the DBM(deterministic Boltzmann machine) network with quantized connection weight. The performance of proposed algorithm is tested with the 2-input XOR problem and the 3-input parity problem through computer simulations. The simulation results show that our algorithm is efficient for quantized connection neural networks.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.32B no.12
• /
• pp.1652-1662
• /
• 1995

In this paper, a hybrid neural network is proposed to improve the learning ability of a neural network. The union of the characteristics of a Self-Organizing Neural Network model and of multi-layer perceptron model using the backpropagation learning method gives us the advantage of reduction of the learning error and the learning time. In learning process, the proposed hybrid neural network reduces the number of nodes in hidden layers to reduce the calculation time. And this proposed neural network uses the fuzzy feedback values, when it updates the responding region of each node in the hidden layer. To show the effectiveness of this proposed hybrid neural network, the boolean function(XOR, 3Bit Parity) and the solution of inverse kinematics are used. Finally, this proposed hybrid neural network is applied to the visual tracking control of a PUMA560 robot, and the result data is presented.

• Proceedings of the Computational Structural Engineering Institute Conference
• /
• 1998.04a
• /
• pp.216-225
• /
• 1998

Although artificial neural network based on backpropagation algorithm is an excellent system simulator, it has still unsolved problems of its structure-decision and learning method. That is, we cannot find a general approach to decide the structure of the neural network and cannot train it satisfactorily because of the local optimum point which it frequently falls into. In addition, although there are many successful applications using backpropagation learning algorithm, there are few efforts to improve the learning algorithm itself. In this study, we suggest a general way to construct the hidden layer of the neural network using binary genetic algorithm and also propose the various learning methods by which the global minimum value of the teaming error can be obtained. A XOR problem and line heating problems are investigated as examples.

• The Transactions of the Korean Institute of Electrical Engineers A
• /
• v.48 no.2
• /
• pp.82-88
• /
• 1999

In this paper, we propose a new structure optimization method of multilayer neural networks which begin and carry out learning from a bigger network. This method redundant links and neurons according to the rough set theory. In order to find redundant links, we analyze the variations of all weights and output errors in every step of the learning process, and then make the decision table from their variation of weights and output errors. We can find the redundant links from the initial structure by analyzing the decision table using the rough set theory. This enables us to build a structure as compact as possible, and also enables mapping between input and output. We show the validity and effectiveness of the proposed algorithm by applying it to the XOR problem.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2000.11a
• /
• pp.409-412
• /
• 2000

본 논문에서는 기존의 결정론적 볼츠만 머신의 학습알고리듬을 수정하여 양자화결합을 갖는 볼츠만 머신에도 적용할 수 있는 알고리듬을 제안하였다. 제안한 알고리듬은 2-입력 XOR문제와 3-입력 패리티문제에 적용하여 성능을 분석하였다. 그 결과 하중이 대폭적으로 양자화된 네트워크도 학습이 가능하다는 것은 은닉 뉴런수를 증가시키면 한정된 하중값의 범위로 유지할 수 있다는 것을 보여주었다. 또한 1회에 갱신하는 하중의 개수 m$_{s}$를 제어함으로써 학습계수를 제어하는 효과가 얻어지는 것을 확인하였다..

• Proceedings of the Korea Inteligent Information System Society Conference
• /
• 2003.05a
• /
• pp.484-489
• /
• 2003

본 논문에서는 역전파 알고리즘의 성능 개선을 위해 퍼지 논리 시스템을 이용한 학습률 자동 조정 방법을 제안한다. 제안된 방법은 목표값과 출력값의 차이에 대한 절대값이 $\varepsilon$ 보다 적거나 같으면 정확성으로 분류하고 크면 부정확성으로 분류한다. 정확성의 총 개수를 퍼지 논리 시스템에 적용하여 학습률과 모멘텀을 동적으로 조정한다. 제안된 방법을 XOR 문제와 숫자패턴 문제에 적용하여 실험한 결과, 기존의 역전파 알고리즘, 모멘텀 방식, Jacob의 delta-bar-delta 방식보다 성능이 개선됨을 확인하였다.

• Journal of Korea Multimedia Society
• /
• v.2 no.4
• /
• pp.490-495
• /
• 1999

In this paper, a method of improving the learning time and convergence rate is proposed to exploit the advantages of artificial neural networks and fuzzy theory to neuron structure. This method is applied to the XOR Problem, n bit parity problem which is used as the benchmark in neural network structure, and recognition of digit image in the vehicle plate image for practical image application. As a result of the experiments, it does not always guarantee the convergence. However, the network showed improved the teaming time and has the high convergence rate. The proposed network can be extended to an arbitrary layer Though a single layer structure Is considered, the proposed method has a capability of high speed 3earning even on large images.