• Journal of the Korean Institute of Intelligent Systems
• /
• v.11 no.9
• /
• pp.817-821
• /
• 2001

In this paper, a new learning methodology for kernel methods that results in a sparse representation of kernel space from the training patterns for classification problems is suggested. Among the traditional algorithms of linear discriminant function, this paper shows that the relaxation procedure can obtain the maximum margin separating hyperplane of linearly separable pattern classification problem as SVM(Support Vector Machine) classifier does. The original relaxation method gives only the necessary condition of SV patterns. We suggest the sufficient condition to identify the SV patterns in the learning epoches. For sequential learning of kernel methods, extended SVM and kernel discriminant function are defined. Systematic derivation of learning algorithm is introduced. Experiment results show the new methods have the higher or equivalent performance compared to the conventional approach.

• The Journal of the Acoustical Society of Korea
• /
• v.21 no.5
• /
• pp.430-437
• /
• 2002

Having a variety of good characteristics against other pattern recognition techniques, the multilayer perceptron (MLP) has been widely used in speech recognition and speaker recognition. But, it is known that the error backpropagation (EBP) algorithm that MLP uses in learning has the defect that requires restricts long learning time, and it restricts severely the applications like speaker recognition and speaker adaptation requiring real time processing. Because the learning data for pattern recognition contain high redundancy, in order to increase the learning speed it is very effective to use the online-based learning methods, which update the weight vector of the MLP by the pattern. A typical online EBP algorithm applies the fixed learning rate for each update of the weight vector. Though a large amount of speedup with the online EBP can be obtained by choosing the appropriate fixed rate, firing the rate leads to the problem that the algorithm cannot respond effectively to different learning phases as the phases change and the number of patterns contributing to learning decreases. To solve this problem, this paper proposes a Changing rate and Omitting patterns in Instant Learning (COIL) method to apply the variable rate and the only patterns necessary to the learning phase when the phases come to change. In this paper, experimentations are conducted for speaker verification and speech recognition, and results are presented to verify the performance of the COIL.

• English Language & Literature Teaching
• /
• v.12 no.1
• /
• pp.131-158
• /
• 2006

The purpose of the present study is to explore an effective way of teaching English vocabulary which is geared toward improving students' English communicative competence. This study focuses on English verbs, which may be followed by patterns according to subcategorization. Learning verbs must include learning about patterns as well as meaning in order to improve the ability to use verbs receptively and productively, or communicative competence. On the basis of the language progression proposed by Willis (2003), a teaching strategy which helps learners learn English verb patterns effectively and systematically was proposed. The effect of the teaching strategy was investigated. The subjects of the experimental group who learned English verb patterns intentionally through the teaching strategy proposed by this study significantly improved themselves in the ability to use them receptively and productively. This result shows that the teaching strategy including improvisation, recognition, rehearsal, system building, exploration and consolidation is helpful to improving communicative competence.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.31B no.5
• /
• pp.134-140
• /
• 1994

In this paper, an algorithm of CBAM(Combination Bidirectional Associative Memory) model proposes, analyzes and tests CBAM model `s performancess by simulating with recalls and recognitions of patterns. In learning-procedure each correlation matrix of training patterns is obtained. As each correlation matrix's some elements correspond to juxtaposition, all correlation matrices are merged into one matrix (Combination Correlation Matrix, CCM). In recall-procedure, CCM is decomposed into a number of correlation matrices by spiliting its elements into the number of elements corresponding to all training patterns. Recalled patterns are obtained by multiplying input pattern with all correlation matrices and selecting a pattern which has the smallest value of energy function. By using a CBAM model, we have some advantages. First, all pattern having less than 20% of noise can be recalled. Second, memory capacity of CBAM model, can be further increased to include English alphabets or patterns. Third, learning time of CBAM model can be reduced greatly because of operation to make CCM.

• Journal of Elementary Mathematics Education in Korea
• /
• v.5 no.1
• /
• pp.1-18
• /
• 2001

This note includes that repeating patterns, knowledge of odd and even numbers, and the patterns in processing and learning addition facts. The potential to mathematical development of repeating patterns is Idly realized if the unit of repeat is recognized. Through the partition of numbers greater then 9 into two equal sets and into sets of 2s, It is necessary the teaching of children's knowledge of odd and even numbers. Being taught derivation strategies through patterns in numbers, we suggest that the teaching seguence to accelerate development of children's learning of additions facts.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2001.12a
• /
• pp.60-64
• /
• 2001

In this paper, a new learning methodology for Kernel Methods is suggested that results in a sparse representation of kernel space from the training patterns for classification problems. Among the traditional algorithms of linear discriminant function(perceptron, relaxation, LMS(least mean squared), pseudoinverse), this paper shows that the relaxation procedure can obtain the maximum margin separating hyperplane of linearly separable pattern classification problem as SVM(Support Vector Machine) classifier does. The original relaxation method gives only the necessary condition of SV patterns. We suggest the sufficient condition to identify the SV patterns in the learning epochs. Experiment results show the new methods have the higher or equivalent performance compared to the conventional approach.

• 제어로봇시스템학회:학술대회논문집
• /
• 1993.10a
• /
• pp.870-876
• /
• 1993

This paper presents a binary clustering network (BCN) and a heuristic algorithm to detect pitch for recognition of keywords in continuous speech. In order to classify nonlinear patterns, BCN separates patterns into binary clusters hierarchically and links same patterns at root level by using the supervised learning and the unsupervised learning. BCN has many desirable properties such as flexibility of dynamic structure, high classification accuracy, short learning time, and short recall time. Pitch Detection algorithm is a heuristic model that can solve the difficulties such as scaling invariance, time warping, time-shift invariance, and redundance. This recognition algorithm has shown recognition rates as high as 95% for speaker-dependent as well as multispeaker-dependent tests.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.6
• /
• pp.2806-2825
• /
• 2018

Unsupervised learning has shown good performance on image, video and audio classification tasks, and much progress has been made so far. It studies how systems can learn to represent particular input patterns in a way that reflects the statistical structure of the overall collection of input patterns. Many promising deep learning systems are commonly trained by the greedy layerwise unsupervised learning manner. The performance of these deep learning architectures benefits from the unsupervised learning ability to disentangling the abstractions and picking out the useful features. However, the existing unsupervised learning algorithms are often difficult to train partly because of the requirement of extensive hyperparameters. The tuning of these hyperparameters is a laborious task that requires expert knowledge, rules of thumb or extensive search. In this paper, we propose a simple and effective unsupervised feature learning algorithm for image classification, which exploits an explicit optimizing way for population and lifetime sparsity. Firstly, a sparse target matrix is built by the competitive rules. Then, the sparse features are optimized by means of minimizing the Euclidean norm ($L_2$) error between the sparse target and the competitive layer outputs. Finally, a classifier is trained using the obtained sparse features. Experimental results show that the proposed method achieves good performance for image classification, and provides discriminative features that generalize well.

• The Journal of Korean Association of Computer Education
• /
• v.6 no.4
• /
• pp.171-180
• /
• 2003

The recent paradigm of web-based teaching-learning is changing into a direction that analyzes the learning patterns of learners on the basis of learners' ability, aptitude, request, interest, learning history, activity profile, etc. and provides adaptive environment with individual learners The present study analyzed learners' learning patterns using data on learning activities and developed a personalization system that provides learning environment adapted to individual learners. This study customized in three aspects, which are recommendation of learning path, recommendation of interface and recommendation of interaction, through Web mining. The personalization system developed in this study was proved to be effective in improving individual learners' satisfaction with learning in Web-based teaching-learning environment.

• The Transactions of the Korean Institute of Electrical Engineers A
• /
• v.48 no.11
• /
• 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.