• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2003년도 학술회의 논문집 정보 및 제어부문 A
• /
• pp.171-174
• /
• 2003

In this paper, a Learning module for a reconfigurable neural network processor(ERNIE) was proposed for an On-chip learning. The existing reconfigurable neural network processor(ERNIE) has a much better performance than the software program but it doesn't support On-chip learning function. A learning module which is based on Back Propagation algorithm was designed for a help of this weak point. A pipeline structure let the learning module be able to update the weights rapidly and continuously. It was tested with five types of alphabet font to evaluate learning module. It compared with C programed neural network model on PC in calculation speed and correctness of recognition. As a result of this experiment, it can be found that the neural network processor(ERNIE) with learning module decrease the neural network training time efficiently at the same recognition rate compared with software computing based neural network model. This On-chip learning module showed that the reconfigurable neural network processor(ERNIE) could be a evolvable neural network processor which can fine the optimal configuration of network by itself.

• 대한전기학회논문지:시스템및제어부문D
• /
• 제53권12호
• /
• pp.804-810
• /
• 2004

There are two important things for the general purpose neural network processor. The first is a capability to build various structures of neural network, and the second is to be able to support suitable learning method for that neural network. Some way to process various learning algorithms is required for on-chip learning, because the more neural network types are to be handled, the more learning methods need to be built into. In this paper, an improved hardware structure is proposed to compute various kinds of learning algorithms flexibly. The hardware structure is based on the existing modular neural network structure. It doesn't need to add a new circuit or a new program for the learning process. It is shown that rearrangements of the existing processing elements can produce several neural network learning modules. The performance and utilization of this module are analyzed by comparing with other neural network chips.

• 전자공학회논문지B
• /
• 제32B권12호
• /
• 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.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제5권1호
• /
• pp.76-82
• /
• 2005

Speech signal has various features of speakers. This feature is extracted from speech signal processing. The speaker is identified by the speaker identification system. In this paper, we propose the speaker identification system that uses the incremental learning based on neural network. Recorded speech signal through the microphone is blocked to the frame of 1024 speech samples. Energy is divided speech signal to voiced signal and unvoiced signal. The extracted 12 orders LPC cpestrum coefficients are used with input data for neural network. The speakers are identified with the speaker identification system using the neural network. The neural network has the structure of MLP which consists of 12 input nodes, 8 hidden nodes, and 4 output nodes. The number of output node means the identified speakers. The first output node is excited to the first speaker. Incremental learning begins when the new speaker is identified. Incremental learning is the learning algorithm that already learned weights are remembered and only the new weights that are created as adding new speaker are trained. It is learning algorithm that overcomes the fault of neural network. The neural network repeats the learning when the new speaker is entered to it. The architecture of neural network is extended with the number of speakers. Therefore, this system can learn without the restricted number of speakers.

• 한국지능시스템학회논문지
• /
• 제20권5호
• /
• pp.672-676
• /
• 2010

본 논문은 연결강도를 조정할 때 결정 경계선 근처에 있는 데이터를 더 반영하는 학습법칙을 제안하였다. 이 학습법칙은 outlier가 결정 경계선에 미치는 영향을 줄여 더 나은 결정 경계선을 형성하도록 한다. 제안하는 학습법칙을 IAFC(Integrated Adaptive Fuzzy Clustering) 신경회로망의 구조에 적용하였다. IAFC 신경회로망은 배운 것을 유지하는 안정성이 있으면서, 새로운 것을 배울 수 있는 안정성이 있다. 이 퍼지 신경회로망의 성능과 LVQ(Learning Vector Quantization) 신경회로망 및 오류역전파 신경회로망의 성능과 비교하였다. 실험결과 제안하는 퍼지 신경회로망의 성능이 우수함을 보여주었다.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2005년도 ICCAS
• /
• pp.421-426
• /
• 2005

Fuzzy logic, neural network, fuzzy-neural network play an important as the key technology of linguistic modeling for intelligent control and decision making in complex systems. The fuzzy-neural network (FNN) learning represents one of the most effective algorithms to build such linguistic models. This paper proposes particle swarm optimization algorithm based optimal learning fuzzy-neural network (PSOA-FNN). The proposed learning scheme is the fuzzy-neural network structure which can handle linguistic knowledge as tuning membership function of fuzzy logic by particle swarm optimization algorithm. The learning algorithm of the PSOA-FNN is composed of two phases. The first phase is to find the initial membership functions of the fuzzy neural network model. In the second phase, particle swarm optimization algorithm is used for tuning of membership functions of the proposed model.

• 한국인터넷방송통신학회논문지
• /
• 제12권3호
• /
• pp.201-207
• /
• 2012

RAM 기반 신경망은 2진 신경망(Binary Neural Network, BNN)에 복수개의 정보 저장 비트를 두어 교육의 반복 횟수를 누적하도록 구성된 가중치를 가지지 않는(weightless) 신경회로망으로서 한 번의 교육만으로 학습이 이루어지는 효율성이 뛰어난 신경회로망이다. 지도 학습에 기반을 둔 RAM 기반 신경망은 패턴 인식 분야에는 우수한 성능을 보이는 반면, 비지도 학습에 의해 패턴을 구분해야 하는 범주화 연구에는 적합하지 않은 모델로 분류된다. 본 논문에서는 비지도 학습 알고리즘을 제안하여 RAM 기반 신경망으로 패턴 범주화를 수행한다. 제안된 비지도 학습 알고리즘에 의해 RAM 기반 신경망은 입력 패턴에 따라 자율 학습하여 스스로 범주를 생성할 수 있으며, 이를 통해 RAM 기반 신경망이 지도 학습과 비지도 학습이 모두 가능한 복합 모델임을 증명한다. 실험에 사용한 학습 패턴으로는 0에서 9까지의 오프라인 필기체 숫자로 구성된 MNIST 데이터베이스를 사용하였다.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2005년도 ICCAS
• /
• pp.1716-1722
• /
• 2005

Fuzzy logic, neural network, fuzzy-neural network play an important as the key technology of linguistic modeling for intelligent control and decision in complex systems. The fuzzy-neural network (FNN) learning represents one of the most effective algorithms to build such linguistic models. This paper proposes bacteria foraging algorithm based optimal learning fuzzy-neural network (BA-FNN). The proposed learning scheme is the fuzzy-neural network structure which can handle linguistic knowledge as tuning membership function of fuzzy logic by bacteria foraging algorithm. The learning algorithm of the BA-FNN is composed of two phases. The first phase is to find the initial membership functions of the fuzzy neural network model. In the second phase, bacteria foraging algorithm is used for tuning of membership functions of the proposed model.

• 대한전기학회논문지:전력기술부문A
• /
• 제48권11호
• /
• pp.1464-1471
• /
• 1999

This paper introduces complex-valued competitive learning neural network for spatio-temporal pattern recognition. There have been quite a few neural networks for spatio-temporal pattern recognition. Among them, recurrent neural network, TDNN, and avalanche model are acknowledged as standard neural network paradigms for spatio-temporal pattern recognition. Recurrent neural network has complicated learning rules and does not guarantee convergence to global minima. TDNN requires too many neurons, and can not be regarded to deal with spatio-temporal pattern basically. Grossberg's avalanche model is not able to distinguish long patterns, and has to be indicated which layer is to be used in learning. In order to remedy drawbacks of the above networks, unsupervised competitive learning using complex umber is proposed. Suggested neural network also features simultaneous recognition, time-shift invariant recognition, stable categorizing, and learning rate modulation. The network is evaluated by computer simulation with randomly generated patterns.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2004년도 ICCAS
• /
• pp.1296-1301
• /
• 2004

Fuzzy logic, neural network, fuzzy-neural network play an important as the key technology of linguistic modeling for intelligent control and decision making in complex systems. The fuzzy -neural network (FNN) learning represents one of the most effective algorithms to build such linguistic models. This paper proposes learning approach of fuzzy-neural network by immune algorithm. The proposed learning model is presented in an immune based fuzzy-neural network (FNN) form which can handle linguistic knowledge by immune algorithm. The learning algorithm of an immune based FNN is composed of two phases. The first phase used to find the initial membership functions of the fuzzy neural network model. In the second phase, a new immune algorithm based optimization is proposed for tuning of membership functions and structure of the proposed model.