• The Journal of Korean Institute of Next Generation Computing
• /
• v.15 no.2
• /
• pp.7-16
• /
• 2019

Neural networks can be implemented in variety of ways, and specialized chips is being developed for hardware improvement. In order to apply such neural networks to wearable devices, the compactness and the low power operation are essential. In this point of view, a suitable implementation method is a digital circuit design using field programmable gate array (FPGA). To implement this system, the learning algorithm which takes up a large part in neural networks must be implemented within FPGA for better performance. In this paper, a back propagation algorithm among various learning algorithms is implemented using FPGA, and this neural network is verified by OR gate operation. In addition, it is confirmed that this neural network can be used to analyze various users' bio signal measurement results by learning algorithm.

• The Journal of the Acoustical Society of Korea
• /
• v.21 no.6
• /
• pp.522-530
• /
• 2002

This paper introduces a neural network (NN) -based nonlinear predictor for the LP (Linear Prediction) residual. To evaluate the effectiveness of the NN-based nonlinear predictor for LP-residual, we first compared the average prediction gain of the linear long-term predictor with that of the NN-based nonlinear long-term predictor. Then, the effects on the quantization noise of the nonlinear prediction residuals were investigated for the NN-based nonlinear predictor A new NN predictor takes into consideration not only prediction error but also quantization effects. To increase robustness against the quantization noise of the nonlinear prediction residual, a constrained back propagation learning algorithm, which satisfies a Kuhn-Tucker inequality condition is proposed. Experimental results indicate that the prediction gain of the proposed NN predictor was not seriously decreased even when the constrained optimization algorithm was employed.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2000.05a
• /
• pp.27-30
• /
• 2000

본 논문에서는 선형 이진 신경회로망(Linear Binary Neural Network)을 이용하여 이진 영상으로부터 골격(skeleton)을 추출하는 병렬 구조를 제안하였다. 기존의 골격 추출 알고리즘으로부터 이진함수를 추출하고 이를 MSP Term Grouping Algorithm을 이용하여 학습시켰다. 결과에서는 기존의 역전파(Back-propagation) 학습알고리즘을 사용한 신경회로망보다 더 쉽게 하드웨어로 구현할 수 있음을 보여준다.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.33B no.4
• /
• pp.191-200
• /
• 1996

This paper presetns a new fuzzy neural network for fuzzy modeling.The fuzzy neural network is composed of 4 layers and then odes of each layer represent the each step of the if-then fuzzy inference. A heuristic based on the back-propagation algorithm is proposed to ajdust the parameters of the fuzzy nerual network. We prove the feasibility of the network using the experiments on modeling a nonlinear mathematical system and the comparison with previous research.

• Proceedings of the KIEE Conference
• /
• 1999.07g
• /
• pp.2932-2934
• /
• 1999

In this paper, a scheme for recognition of handwritten digits using a multilayer neural network trained with the back-propagation algorithm using generalized delta rule is proposed. The neural network is trained with hand written digit data of different writers and different styles. One of the purpose of the work with neural networks is the minimization of the mean square error(MSE) between actual output and desired one. The back-propagation algorithm is an efficient and very classical method. The back-propagation algorithm for training the weights in a multilayer net uses the steepest descent minimization procedure and the sigmoid threshold function. As an error rate is reduced, recognition rate is improved. Therefore we propose a method that is reduced an error rate.

• Proceedings of the KIEE Conference
• /
• 1999.07g
• /
• pp.2977-2979
• /
• 1999

본 논문에서는 MEBP(Modified Error Back-Propagation) 학습 규칙을 간단한 비선형 회로를 이용하여 구현하였다. 인공 신경 회로망(ANNs : Artificial Neural Networks)은 많은 수의 뉴런을 필요하기 때문에 표준 CMOS 기술을 이용하는 간단한 비선형 시냅스(synapse) 회로는 인공 신경 회로망 구현에 적합하다. 학습회로는 비선형 시냅스 회로. 시그모이드(sigmoid) 회로. 그리고 선형 곱셈기로 구성되어 있다. 학습 회로의 출력은 각 입력 패턴에 따라 유일한 값으로 결정되어진다. 제안한 학술회로를 $2{\times}2{\times}1$과 $2{\times}3{\times}1$ 다층 feedforward 신경 회로망 모델에 적용하였다. MEBP 하드웨어 구현은 HSPICE 회로 시뮬레이터를 이용하여 검증하였다. 제안한 학술 회로는 on-chip 학습회로를 포함한 대규모 신경회로망 구현에 매우 적합하리라 예상된다.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.33B no.1
• /
• pp.144-152
• /
• 1996

In this paper, a pulse-mode digital multilayer neural network with a massively parallel yet compact and flexible network architecture is presented. Algebraicneural operations are replaced by stochastic processes using pseudo-random pulse sequences and simple logic gates are used as basic computing elements. The distributions of the results from the stochastic processes are approximated using the hypergeometric distribution. A statistical model of the noise(error) is developed to estimate the relative accuracy associated with stochastic computing in terms of mean and variance. Numerical character recognition problems are applied to the network to evaluate the network performance and to justify the validity of analytic results based on the developed statistical model. The network architectures are modeled in VHDL using the mixed descriptions of gate-level and register transfer level (RTL). Experiments show that the statistical model successfully predicts the accuracy of the operations performed in the network and that the character classification rate of the network is competitive to that of ordinary Back-Propagation networks.

• Journal of the Korean Institute of Telematics and Electronics T
• /
• v.35T no.3
• /
• pp.46-52
• /
• 1998

In this paper, after inputting the computer with the attached number plate on the vehicle, using it, the color decomposition method and back propagation neural network proposed the extractable method of the vehicle number plate at high speed. This method separated R, G, B signal form input moving vehicle image to computer through video camera, then after transform this R, G, B signal into input image data of the computer by using color depth of vehicle number plate and store up binary value in the memory frame buffer. After adapting character's recognition algorithm, also improving this, by adapting back propagation neural network makes the vehicle number plate recognition system. Also minimalizing the similar color's confusion, adapting horizontal and vertical extracting algorithm by using the vehicle's rectangular architecture shows the extract and character's recognition of the vehicle number plate at high speed.

• Journal of the Korean Society for Precision Engineering
• /
• v.15 no.7
• /
• pp.26-35
• /
• 1998

This paper presents a visual inspection algorithm looking for solder joint defects of IC chips on PCBs (Printed Circuit Boards). In this algorithm, seven features are proposed in order to categorize the solder joints into four classes such as normal, insufficient, excess, and no solder, and optimal back-propagation network is determined by error evaluation which depend on the number of neurons in hidden and out-put layers and selection of the features. In the end, a good accuracy of classification performance, an optimal determination of network structure and the effectiveness of chosen seven features are examined by experiment using proposed inspection algorithm.

• Journal of Intelligence and Information Systems
• /
• v.5 no.1
• /
• pp.49-64
• /
• 1999

본 연구는 백화점 고객이 신용 카드 신청 요구 시에 작성되는 가입 정보 및 사용되고 있는 고객의 거래 정보는 카드 사용 패턴으로 신용도를 예측하는 여러 방법론을 제시하고 성능을 비교하였다. 가입 정보를 분석하기 위해 역전파 신경망(Back-Propagation Neural Network, BPNN), 사례기반추론(Case-Based reasoning)을, 거래 정보를 분석하기 위해 역전파 신경망과 더불어 시간지연 신경망(Time-Delayed Neural Network, TDNN)을 각각 사용하여 그 결과를 비교하였다. 또한 전체시스템의 적중률을 높이기 위햐여, ID3와 신경망을 이용한 Meta-Leaning 방법을 제시하였으며, Meta-Learning 방법과 다른 방법들을 비교, 분석을 하였다. 본 연구에서는 모형 수립과 검증을 위하여 T백화점의 실제 신용 카드 가입 고객 데이터를 이용하여 실험하였다. 데이터의 성격에 따라 각 모델의 예측력에는 차이가 나타났으나, 신경망 모형의 예측력이 우수하였으며, 시간적 특성을 고려하는 시간지연 신경회로망 모형의 예측력은 더욱 우수하게 나타났다. 또한 Meta-Learning 모형을 사용하면 예측력이 더 높아진다는 것을 확인할 수 있었다.