• 제어로봇시스템학회:학술대회논문집
• /
• 1989.10a
• /
• pp.653-662
• /
• 1989

Cerebellar Model Arithmetic Controller (CMAC) has been introduced as an adaptive control function generator. CMAC computes control functions referring to a distributed memory table storing functional values rather than by solving equations analytically or numerically. CMAC has a unique mapping structure as a coarse coding and supervisory delta-rule learning property. In this paper, learning aspects and a convergence of the CMAC were investigated. The efficient training algorithms were developed to overcome the limitations caused by the conventional maximum error correction training and to eliminate the accumulated learning error caused by a sequential node training. A nonlinear function generator and a motion generator for a two d.o.f. manipulator were simulated. The efficiency of the various learning algorithms was demonstrated through the cpu time used and the convergence of the rms and maximum errors accumulated during a learning process. A generalization property and a learning effect due to the various gains were simulated. A uniform quantizing method was applied to cope with various ranges of input variables efficiently.

• 한국기계연구소 소보
• /
• s.19
• /
• pp.93-115
• /
• 1989

Cerebellar Model Arithmetic Controller(CMAC) has been introduced as an adaptive control function generator. CMAC computes control functions referring to a distributed memory table storing functional values rather than by solving equations analytically or numerically. CMAC has a unique mapping structure as a coarse coding and supervisory delta-rule learning property. In this paper, learning aspects and a convergence of the CMAC were investigated. The efficient training algorithms were developed to overcome the limitations caused by the conventional maximum error correction training and to eliminate the accumulated learning error caused by a sequential node training. A nonlinear function generator and a motion generator for a two d. o. f. manipulator were simulated. The efficiency of the various learning algorithms was demonstrated through the cpu time used and the convergence of the rms and maximum errors accumulated during a learning process; A generalization property and a learning effect due to the various gains were simulated. A uniform quantizing method was applied to cope with various ranges of input variables efficiently.

• Journal of Fisheries and Marine Sciences Education
• /
• v.27 no.4
• /
• pp.1160-1171
• /
• 2015

The purpose of this study is to design and develop a computer based learning and test system, which supports not only testing learner's ability but also learning contents with giving feedback and hint. In order to design and develop a computer based learning and test system, Visual Basic dot Net software is used. The system works in three stages: sequential problem solving stage, randomized problem solving stage, and the challenge stage of pass/fail. The results of this study are as follows: (a) We propose the context of design for the computer based learning and test system. (b) We design and develop items display function with sequential and random algorithm in this system. (c) We design and develop pass/fail function by applying SPRT(Sequential Probability Ratio Testing) algorithm in the computer based learning and test system.

• International Journal of Advanced Culture Technology
• /
• v.6 no.4
• /
• pp.262-265
• /
• 2018

Deep learning, a sub-field of machine learning changing the prospects of artificial intelligence (AI) because of its recent advancements and application in various field. Deep learning deals with algorithms inspired by the structure and function of the brain called artificial neural networks. This works reviews basic architecture and recent advancement of deep structured learning. It also describes contemporary applications of deep structured learning and its advantages over the treditional learning in artificial interlligence. This study is useful for the general readers and students who are in the early stage of deep learning studies.

• Journal of Engineering Education Research
• /
• v.16 no.1
• /
• pp.3-14
• /
• 2013

The previously developed practical inquiry activity supporting tools, deduced from the design principles and implementation principles based on the study of precedent researches and theories, applicable to conceptual learning in engineering education were implemented to an on-line learning community, a web-based Windows application, to find out its effectiveness in actual classroom situation through experimental research. The On-line learning community includes the inquiry activity menu to implement learning procedure of inquiry based conceptual learning, the functions supporting the communication among participants, the information sharing function, the scheduling function of class and inquiry activity, the mentoring function, and the evaluation of on-line activities of learners. Experimental study were also conducted in order to analyze the effects of inquiry activity supporting tools on inquiry based conceptual learning in engineering education.

• 제어로봇시스템학회:학술대회논문집
• /
• 1996.10a
• /
• pp.111-114
• /
• 1996

This paper proposes a robust control method using Universal Learning Network(U.L.N.) and second order derivatives of U.L.N.. Robust control considered here is defined as follows. Even if external input (equal to reference input in this paper) to the system at control stage changes awfully from that at learning stage, the system can be controlled so as to maintain a good performance. In order to realize such a robust control, a new term concerning the perturbation is added to a usual criterion function. And parameter variables are adjusted so as to minimize the above mentioned criterion function using the second order derivative of the criterion function with respect to the parameters.

• Proceedings of the Acoustical Society of Korea Conference
• /
• 1994.06c
• /
• pp.407-410
• /
• 1994

In this paper, we describe the new unsuperivised learning algorithm, SASOM. It can solve the defects of the conventional SOM that the state of network can't converge to the minimum point. The proposed algorithm uses the object function which can evaluate the state of network in learning and adjusts the learning rate flexibly according to the evaluation of the object function. We implement the simulated annealing which is applied to the conventional network using the object function and the learning rate. Finally, the proposed algorithm can make the state of network converged to the global minimum. Using the two-dimensional input vectors with uniform distribution, we graphically compared the ordering ability of SOM with that of SASOM. We carried out the recognitioin on the new algorithm for all Korean phonemes and some continuous speech.

• 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.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1998.06a
• /
• pp.399-403
• /
• 1998

In this paper, we proposed a new fuzzy supervised learning algorithm. We construct, and train, a new type fuzzy neural net to model the linear activation function. Properties of our fuzzy neural net include : (1) a proposed linear activation function ; and (2) a modified delta rule for learning algorithm. We applied this proposed learning algorithm to exclusive OR,3 bit parity using benchmark in neural network and pattern recognition problems, a kind of image recognition.

• Proceedings of the Korean Society of Machine Tool Engineers Conference
• /
• 1997.10a
• /
• pp.82-87
• /
• 1997

This paper presents a new approach to the design of cruise control system of a mobile robot with two drive wheel. The proposed control scheme uses a Gaussian function as a unit function in the fuzzy-neural network, and back propagation algorithm to train the fuzzy-neural network controller in the framework of the specialized learning architecture. It is proposed a learning controller consisting of two neural network-fuzzy based on independent reasoning and a connection net with fixed weights to simply the neural networks-fuzzy. The performance of the proposed controller is shown by performing the computer simulation for trajectory tracking of the speed and azimuth of a mobile robot driven by two independent wheels.