• Journal of Information Processing Systems
• /
• v.17 no.3
• /
• pp.441-452
• /
• 2021

Federated learning provides an efficient integrated model for distributed data, allowing the local training of different data. Meanwhile, the goal of multi-task learning is to simultaneously establish models for multiple related tasks, and to obtain the underlying main structure. However, traditional federated multi-task learning models not only have strict requirements for the data distribution, but also demand large amounts of calculation and have slow convergence, which hindered their promotion in many fields. In our work, we apply the rank constraint on weight vectors of the multi-task learning model to adaptively adjust the task's similarity learning, according to the distribution of federal node data. The proposed model has a general framework for solving optimal solutions, which can be used to deal with various data types. Experiments show that our model has achieved the best results in different dataset. Notably, our model can still obtain stable results in datasets with large distribution differences. In addition, compared with traditional federated multi-task learning models, our algorithm is able to converge on a local optimal solution within limited training iterations.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.23 no.12
• /
• pp.1542-1550
• /
• 2019

Legacy studies for classifying arrhythmia have been studied to improve the accuracy of classification, Neural Network, Fuzzy, etc. Deep learning is most frequently used for arrhythmia classification using error backpropagation algorithm by solving the limit of hidden layer number, which is a problem of neural network. In order to apply a deep learning model to an ECG signal, it is necessary to select an optimal model and parameters. In this paper, we propose optimal parameter extraction method based on a deep learning. For this purpose, R-wave is detected in the ECG signal from which noise has been removed, QRS and RR interval segment is modelled. And then, the weights were learned by supervised learning method through deep learning and the model was evaluated by the verification data. The detection and classification rate of R wave and PVC is evaluated through MIT-BIH arrhythmia database. The performance results indicate the average of 99.77% in R wave detection and 97.84% in PVC classification.

• Journal of IKEEE
• /
• v.25 no.4
• /
• pp.644-649
• /
• 2021

Self-Imitation Learning is a simple off-policy actor-critic algorithm that makes an agent find an optimal policy by using past good experiences. In case that Self-Imitation Learning is combined with reinforcement learning algorithms that have actor-critic architecture, it shows performance improvement in various game environments. However, its applications are limited to reinforcement learning algorithms that have actor-critic architecture. In this paper, we propose a method of applying Self-Imitation Learning to Deep Q-Network which is a value-based deep reinforcement learning algorithm and train it in various game environments. We also show that Self-Imitation Learning can be applied to Deep Q-Network to improve the performance of Deep Q-Network by comparing the proposed algorithm and ordinary Deep Q-Network training results.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.16 no.4
• /
• pp.270-275
• /
• 2016

We present an approach for acceleration actor-critic algorithm for reinforcement learning with continuous action space. Actor-critic algorithm has already proved its robustness to the infinitely large action spaces in various high dimensional environments. Despite that success, the main problem of the actor-critic algorithm remains the same-speed of convergence to the optimal policy. In high dimensional state and action space, a searching for the correct action in each state takes enormously long time. Therefore, in this paper we suggest a search accelerating function that allows to leverage speed of algorithm convergence and reach optimal policy faster. In our method, we assume that actions may have their own distribution of preference, that independent on the state. Since in the beginning of learning agent act randomly in the environment, it would be more efficient if actions were taken according to the some heuristic function. We demonstrate that heuristically-accelerated actor-critic algorithm learns optimal policy faster, using Educational Process Mining dataset with records of students' course learning process and their grades.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.20 no.2
• /
• pp.399-407
• /
• 1996

A fuzzy learning algorithm to get the optimal fuzzy rules is presented in this paper. The algorithm introduces a reference model to generate a desired output and a performance index funtion instead of the performance index table. The performance index funtion is a cost function based on the error and error-rate between the reference and plant output. The cost function is minimized by a gradient method and the control input is also updated. In this case, the control rules which generate the desired response can be obtained by changing the portion of the error-rate in the cost funtion. In SISO(Single-Input Single- Output)plant, only by the learning delay, it is possible to experss the plant model and to get the desired control rules. In the long run, this algorithm gives us the good control rules with a minimal amount of prior informaiton about the environment.

• Proceedings of the KIEE Conference
• /
• 1999.07c
• /
• pp.1279-1281
• /
• 1999

The learning automaton is an automaton to update systematically the strategy for enhancing the performance in response to the output results, and several schemes of learning automata have been presented. In this paper, S-model learning automata are applied to achieving a best compromise solution between an optimal solution for economic operation and an optimal solution for stable operation of the power system under the circumstance that the loads vary randomly. It is shown that learning automata are applied satisfactorily to the multiobjective optimization problem for obtaining the best tradeoff among the conflicting economy and stability objectives of power systems.

• Journal of the Korean Operations Research and Management Science Society
• /
• v.31 no.2
• /
• pp.69-85
• /
• 2006

Transductive Support Vector Machine(TSVM) is one of semi-supervised learning algorithms which exploit the domain structure of the whole data by considering labeled and unlabeled data together. Although it was proposed several years ago, there has been no efficient algorithm which can handle problems with more than hundreds of training examples. In this paper, we propose an efficient branch-and-bound algorithm which can solve large-scale TSVM problems with thousands of training examples. The proposed algorithm uses two bounding techniques: min-cut bound and reduced SVM bound. The min-cut bound is derived from a capacitated graph whose cuts represent a lower bound to the optimal objective function value of the dual problem. The reduced SVM bound is obtained by constructing the SVM problem with only labeled data. Experimental results show that the accuracy rate of TSVM can be significantly improved by learning from the optimal solution of TSVM, rather than an approximated solution.

• Journal of Information Processing Systems
• /
• v.16 no.5
• /
• pp.1223-1230
• /
• 2020

Recently, extensive studies have been conducted to apply deep learning to reinforcement learning to solve the state-space problem. If the state-space problem was solved, reinforcement learning would become applicable in various fields. For example, users can utilize dance-tutorial systems to learn how to dance by watching and imitating a virtual instructor. The instructor can perform the optimal dance to the music, to which reinforcement learning is applied. In this study, we propose a method of reinforcement learning in which the action space is dynamically adjusted. Because actions that are not performed or are unlikely to be optimal are not learned, and the state space is not allocated, the learning time can be shortened, and the state space can be reduced. In an experiment, the proposed method shows results similar to those of traditional Q-learning even when the state space of the proposed method is reduced to approximately 0.33% of that of Q-learning. Consequently, the proposed method reduces the cost and time required for learning. Traditional Q-learning requires 6 million state spaces for learning 100,000 times. In contrast, the proposed method requires only 20,000 state spaces. A higher winning rate can be achieved in a shorter period of time by retrieving 20,000 state spaces instead of 6 million.

• Educational Technology International
• /
• v.19 no.2
• /
• pp.229-254
• /
• 2018

Universities in Korea have driven universities' new attempts to adopt more learner-centered and active learning in English. Problem-based Learning (PBL) is one of the well-known constructive teaching and learning methodologies in higher education. Our research goal was to design and develop the optimal PBL practices for a college physics course taught in English to promote learning and course satisfaction. For four semesters, we have tried and adjusted PBL components, and looked at the trend of the exam scores and group work achievement in each semester. We found that the number of problems and the duration of problem solving are the critical factors that influence the effect of PBL in a college physics course taught in English by going through iterative implementation. The iterative process of applying, designing, and constructing PBL to physics classes was meaningful not only in that we have found the optimal PBL model for learning a college physics course, but also in that we have been reflecting on the continuous interaction with learners during the course.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2003.09b
• /
• pp.95-98
• /
• 2003

In this paper, an adaptive fuzzy neural control of unknown nonlinear systems based on the rapid learning algorithm is proposed for optimal parameterization. We combine the advantages of fuzzy control and neural network techniques to develop an adaptive fuzzy control system for updating nonlinear parameters of controller. The Fuzzy Neural Network(FNN), which is constructed by an equivalent four-layer connectionist network, is able to learn to control a process by updating the membership functions. The free parameters of the AFN controller are adjusted on-line according to the control law and adaptive law for the purpose of controlling the plant track a given trajectory and it's initial values are off-line preprocessing, In order to improve the convergence of the learning process, we propose a rapid learning algorithm which combines the error back-propagation algorithm with Aitken's $\delta$$\^$2/ algorithm. The heart of this approach ls to reduce the computational burden during the FNN learning process and to improve convergence speed. The simulation results for nonlinear plant demonstrate the control effectiveness of the proposed system for optimal parameterization.