• Proceedings of the Korea Contents Association Conference
• /
• 2015.05a
• /
• pp.65-66
• /
• 2015

다층퍼셉트론은 학습성능이 우수하여 많은 패턴인식 문제에 응용되고 있다. 그 응용문제 중 하나인 갑상선 질환 진단 문제는 학습이 어려운 문제이다. 이 논문에서는 다층퍼셉트론으로 갑상선 진단 질환을 학습하는 여러 방법을 비교하고, 성능이 좋지 않은 원인을 토대로 성능 향상을 위한 방법을 제시하겠다.

• Proceedings of the Korea Contents Association Conference
• /
• 2010.05a
• /
• pp.3-4
• /
• 2010

다층퍼셉트론의 구조를 결정할 때 중간층 노드 수를 정하는 부분이 성능에 큰 영향을 미친다. 이 논문에서는 처음에 중간층 노드수를 임의로 크게 설정한 다음, 학습의 진행에 따라 중간층 노드 수를 축소시키는 방법을 제안한다. 제안한 방법은 중간층 노드들 간의 상관관계를 활용한 방법으로 이전의 방법들보다 훨씬 간단하다.

• The Journal of the Acoustical Society of Korea
• /
• v.22 no.5
• /
• pp.360-366
• /
• 2003

Although multilayer perceptrons (MLPs) present several advantages against other pattern recognition methods, MLP-based speaker verification systems suffer from slow enrollment speed caused by many background speakers to achieve a low verification error. To solve this problem, the quantitative discriminative cohort speakers (QnDCS) method, by introducing the cohort speakers method into the systems, reduced the number of background speakers required to enroll speakers. Although the QnDCS achieved the goal to some extent, the improvement rate for the enrolling speed was still unsatisfactory. To improve the enrolling speed, this paper proposes the qualitative DCS (QlDCS) by introducing a qualitative criterion to select less background speakers. An experiment for both methods is conducted to use the speaker verification system based on MLPs and continuants, and speech database. The results of the experiment show that the proposed QlDCS method enrolls speakers in two times shorter time than the QnDCS does over the online error backpropagation(EBP) method.

• Computers and Concrete
• /
• v.4 no.6
• /
• pp.477-497
• /
• 2007

The ultrasonic pulse velocity method has been widely used to evaluate the quality of concrete and assess the structural integrity of concrete structures. But its use for predicting strength is still limited since there are many variables affecting the relationship between strength and pulse velocity of concrete. This study is focused on establishing a complicated correlation between known input data, such as pulse velocity and mixture proportions of concrete, and a certain output (compressive strength of concrete) using artificial neural networks (ANN). In addition, the results predicted by the developed multilayer perceptrons (MLP) networks are compared with those by conventional regression analysis. The result shows that the correlation between pulse velocity and compressive strength of concrete at various ages can be well established by using ANN and the accuracy of the estimates depends on the quality of the information used to train the network. Moreover, compared with the conventional approach, the proposed method gives a better prediction, both in terms of coefficients of determination and root-mean-square error.

• The Journal of the Korea Contents Association
• /
• v.10 no.6
• /
• pp.166-174
• /
• 2010

Based on the theoretical results that multi-layer feedforward neural networks with enough hidden nodes are universal approximators, we usually use three-layer MLP's(multi-layer perceptrons) consisted of input, hidden, and output layers for many application problems. However, this conventional three-layer architecture of MLP shows poor generalization performance in some applications, which are complex with various features in an input vector. For the performance improvement, this paper proposes a hierarchical architecture of MLP especially when each part of inputs has a special information. That is, one input vector is divided into sub-vectors and each sub-vector is presented to a separate MLP. These lower-level MLPs are connected to a higher-level MLP, which has a role to do a final decision. The proposed method is verified through the simulation of protein disorder prediction problem.

• Journal of the Korea Society of Computer and Information
• /
• v.16 no.8
• /
• pp.39-47
• /
• 2011

Ergezinger's method, one of the layer-by-layer algorithms used for multilyer perceptrons, consists of an output node and can make premature saturations in the output's weight because of using linear least squared method in the output layer. These saturations are obstacles to learning time and covergence. Therefore, this paper expands Ergezinger's method to be able to use an output vector instead of an output node and introduces a learning rate to improve learning time and convergence. The learning rate is a variable rate that reflects the correlation coefficient between new weight and previous weight while updating hidden's weight. To compare the proposed method with Ergezinger's method, we tested iris recognition and nonlinear approximation. It was found that the proposed method showed better results than Ergezinger's method in learning convergence. In the CPU time considering correlation coefficient computation, the proposed method saved about 35% time than the previous method.

• International Journal of Contents
• /
• v.9 no.4
• /
• pp.11-15
• /
• 2013

"Protein Folding Problem" is considered to be one of the "Great Challenges of Computer Science" and prediction of disordered protein is an important part of the protein folding problem. Machine learning models can predict the disordered structure of protein based on its characteristic of "learning from examples". Among many machine learning models, we investigate the possibility of multilayer perceptron (MLP) as the predictor of protein disorder. The investigation includes a single hidden layer MLP, multi hidden layer MLP and the hierarchical structure of MLP. Also, the target node cost function which deals with imbalanced data is used as training criteria of MLPs. Based on the investigation results, we insist that MLP should have deep architectures for performance improvement of protein disorder prediction.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2003.10a
• /
• pp.1015-1020
• /
• 2003

Among the techniques to protect private information by adopting biometrics, speaker verification is expected to be widely used due to advantages in convenient usage and implementation cost. Speaker verification should achieve a high degree of the reliability in the verification score, the flexibility in speech text usage, and the efficiency in verification system complexity. Continuants have excellent speaker-discriminant power and the modest number of phonemes in the category, and multilayer perceptrons (MLPs) have superior recognition ability and fast operation speed. In consequence, the two provide viable ways for speaker verification system to obtain the above properties. This paper implements a system to which continuants and MLPs are applied, and evaluates the system using a Korean speech database. The results of the experiment prove that continuants and MLPs enable the system to acquire the three properties.

• Proceedings of the Korea Contents Association Conference
• /
• 2005.11a
• /
• pp.364-370
• /
• 2005

LBL(Layer-By-Layer) algorithms have been proposed to accelerate the training speed of MLPs(Multilayer Perceptrons). In this LBL algorithms, each layer needs a error function for optimization. Especially, error function for hidden layer has a great effect to achieve good performance. In this sense, this paper proposes a new hidden layer error function for improving the performance of LBL algorithm for MLPs. The hidden layer error function is derived from the mean squared error of output layer. Effectiveness of the proposed error function was demonstrated for a handwritten digit recognition and an isolated-word recognition tasks and very fast learning convergence was obtained.

• 제어로봇시스템학회:학술대회논문집
• /
• 2001.10a
• /
• pp.172.6-172
• /
• 2001

In recent years, many attempts have been made to predict the behavior of bonds, currencies, stock, or other economic markets. Most previous experiments used multilayer perceptrons(MLP) for stock market forecasting, The Kospi 200 Index is modeled using different neural networks and fuzzy system predictions. In this paper, a multilayer perceptron architecture, a dynamic polynomial neural network(DPNN) and a fuzzy system are used to predict the Kospi 200 index. The results of prediction is compared with the root mean squared error(RMSE) and the scatter plot. The results show that the fuzzy system is performing slightly better than DPNN and MLP. We can develop the desired fuzzy system by learning methods ...