• 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.

• Journal of IKEEE
• /
• v.12 no.1
• /
• pp.65-74
• /
• 2008

One of the popular methods used for pattern classification is the MBR (Memory-Based Reasoning) algorithm. Since it simply computes distances between a test pattern and training patterns or hyperplanes stored in memory, and then assigns the class of the nearest training pattern, it is notorious for memory usage and can't learn additional information from new data. In order to overcome this problem, we propose an incremental learning algorithm (iMPA). iMPA divides the entire pattern space into fixed number partitions, and generates representatives from each partition. Also, due to the fact that it can not learn additional information from new data, we present iMPA which can learn additional information from new data and not require access to the original data, used to train. Proposed methods have been successfully shown to exhibit comparable performance to k-NN with a lot less number of patterns and better result than EACH system which implements the NGE theory using benchmark data sets from UCI Machine Learning Repository.

• 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.

• The Journal of Information Technology
• /
• v.1 no.1
• /
• pp.65-84
• /
• 1998

The MBR (Memory Based Reasoning) is a supervised learning method that utilizes the distances among the input and trained patterns in its classification, and is also called a distance based learning algorithm. The MBR is based on the k-NN classifier, in which teaming is performed by simply storing training patterns in the memory without any further processing. This paper proposes a new learning algorithm which is more efficient than the traditional k-NN classifier and has incremental learning capability, Furthermore, our proposed algorithm is insensitive to noisy patterns, and guarantees more efficient memory usage.

• Journal of Korea Multimedia Society
• /
• v.20 no.5
• /
• pp.769-781
• /
• 2017

Deep learning networks like Convolutional Neural Networks (CNNs) show successful performances in many computer vision applications such as image classification, object detection, and so on. For implementation of deep learning networks in embedded system with limited processing power and memory, deep learning network may need to be simplified. However, simplified deep learning network cannot learn every possible scene. One realistic strategy for embedded deep learning network is to construct a simplified deep learning network model optimized for the scene images of the installation place. Then, automatic training will be necessitated for commercialization. In this paper, as an intermediate step toward automatic training under fisheye camera environments, we study more precise human localization in fisheye images, and propose an accurate human localization method, Automatic Ground-Truth Labelling Method (AGTLM). AGTLM first localizes candidate human object bounding boxes by utilizing GoogLeNet-LSTM approach, and after reassurance process by GoogLeNet-based CNN network, finally refines them more correctly and precisely(tightly) by applying saliency object detection technique. The performance improvement of the proposed human localization method, AGTLM with respect to accuracy and tightness is shown through several experiments.

• IMMUNE NETWORK
• /
• v.5 no.4
• /
• pp.252-257
• /
• 2005

Background: This study was designed to investigate the effect of exercise training on defense mechanism of chronic degenerative disease, aging, and memory impairments of senescence-accelerated mouse (SAM)P8 under the hypothesis that "Senile dementia may be prevented by regular exercises". Methods: To evaluate the effects of exercise training on the defense mechanism of aging and memory impairment, SAMP8 were divided into two groups, the control group and exercise training groups. the exercise training group were performed with low $(\dot{V}O_2max\;25{\sim}33%)$, middle ($\dot{V}O_2max$ 50%) and high $(\dot{V}O_2max\;66{\sim}75%)$ intensity exercise. All SAMP8 mice were fed experimental diet ad libitum until 4, 8 months, and dead period. Results: Median lifespan in middle exercise group resulted in a significantly increased (23.5% and 18.7%, respectively), whereas these lifespan in high exercise group resulted in an unexpectedly decreased (13.5% and 12.1%, respectively) compared with control group. Body fat levels in 4 and 8 months of age were significantly decreased 43% to 51% in middle exercise group, whereas were remarkably deceased to 57% in high exercise group compared with control group. It is believed that extended median and maximum lifespan may be effected by calory restriction through the exercise training. Acetylcholine (ACh) levels were significantly increased 6.7% and 8.5% in middle and high exercise groups, and also choline acetyltransfease (ChAT) activities were significantly increased 10.3% and 11.9% in middle and high exercise groups. Conclusion: These results suggest that proper and regular exercises such as middle group ($\dot{V}O_2max$ 50%) may play an effective role in attenuating an oxygen radicals and may play an important role in improving a learning and memory impairments of senile dementia.

• The Journal of Korean Physical Therapy
• /
• v.19 no.4
• /
• pp.25-32
• /
• 2007

Purpose: The purpose of this study was to evaluate the effect of computerized neurocognitive function program on cognitive function about memory and attention with stroke. Methods: 24subjects with stroke were recruited. Twelve of subjects received conventional therapy including physical therapy, occupational therapy and language therapy. Another subjects received additional computer assisted cognitive training using Computer-aided Cognitive rehabilitation training system(COMCOG, MaxMedica Inc., 2004). All patients were assessed their cognitive function of memory and attention using Computerized Neurocognitive Function Test(CNT, MaxMedica Inc., 2004) before treatment and 6 weeks after treatment. Results: Before the treatment, two groups showed no difference in cognitive function(p>0.05). After 6 weeks, two groups showed significantly difference in digit span (forward, backward), verbal learning(A5, $A1{\sim}A5$), auditory CPT(n), visual CPT(n)(p<0.05). After treatment, the experimental group showed a significant improvement of digit span(forward, backward), verbal learning(A5, $A1{\sim}A5$), visual span (forward, backward), auditory CPT(n, sec), visual CPT(n, sec), and trail-making (A, B)(p<0.05). Conclusion: Computerized neurocognitive function program would be improved cognitive function of memory and attention in patients with stoke.

• International Journal of Industrial Entomology and Biomaterials
• /
• v.15 no.1
• /
• pp.39-45
• /
• 2007

Extracts of adult worker bodies of Vespa simillima in 2 % NaCl or acidified methanol were administered orally to mice for 70 days. Following this period, memory at one-day and one-month periods, and the effects on scopolamine-induced amnesia were examined using a step-through passive avoidance task. Changes in MK-801-induced disability after 8 days of training, and in memory one month after the trial were also assessed. Mice treated with the 2% NaCl extract showed significant improvement in memory in the behavioral tests one month after the trial, whereas mice receiving the extract in acidified methanol, did not differ from the controls in any trial. The results inidicate that Vespa simillima contains substances acting favorably on the cerebral functions of mammals.

• The Journal of Korean Association of Computer Education
• /
• v.14 no.5
• /
• pp.39-46
• /
• 2011

Serious games are designed for special purposes of education, training, treatment as well as game-like fun and entertainment. Recently, domestic and foreign market of serious game are growing rapidly. By dissemination of smartphone, the global market for serious game will be expanded for various purposes and users. In this paper, we design and implement serious game 'QUICK REMEMBER 20' for memory improvement using smartphone. We analyze game users based on socio-demographic characteristics and evaluate the learning effectiveness of this game with statistic method.

• 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.