• 동의생리병리학회지
• /
• 제19권1호
• /
• pp.254-261
• /
• 2005

The effects on memory and learning ability of the Korean herbal medicine, Xingyo-tang(XGT, 神交湯), which consists of Ginseng Radix(人蔘) 4 g, Liriopis Tuber(麥門冬) 40 g, Morindae Officinalis Radix(巴戟天) 40 g, Biotae Semen(柏子仁) 20 g, Dioscoreae Rhizoma(山藥) 40 g, Euryales Semen(?實) 20 g, Scrophulariae Radix(玄蔘) 40 g, Salviae Miltiorrhizae Radix(丹蔘) 12 g, Poria(茯神) 12 g, Cuscutae Semen(免絲子) 40 g, was investigated. The effects of XGT on learning and memory performance were examined in normal or memory impaired mice by using avoidance tests, Pentobarbital -induced sleep test, fear conditioning task, novel object recognition task, and water maze task. Hot water extract from XGT was used for the studies. Learning ability and memory are based on modifications of synaptic strength among neurons that are simultaneously active. Enhanced synaptic coincidence detection leads to better learning and memory. The XGT-treated (30 mg/100 g and 60 mg/100 g, p.o.) mice exhibit superior ability in learning and memorizing when performing various behavioral tasks. XGT did not affect the passive avoidance responses of normal mice in the step through and step down tests, the conditioned and unconditioned avoidance responses of normal mice in the shuttle box, lever press performance tests, and the ambulatory activity of normal mice in normal condition. In contrast, XGT produced ameliorating effects on the memory retrieval impairment induced by ethanol. XGT also improved the memory consolidation disability induced by electric convulsive shock (ECS). XGT extended the sleeping time induced by pentobarbital dose-dependently, suggesting its transquilizing or antianxiety action. These results suggest that XGT has an improving effect on the impaired learning through the effects on memory registration and retrieval.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2000년도 제15차 학술회의논문집
• /
• pp.174-174
• /
• 2000

Q-learning, based on discrete state and action space, is a most widely used reinforcement Learning. However, this requires a lot of memory and much time for learning all actions of each state when it is applied to a real mobile robot navigation using continuous state and action space Region-based Q-learning is a reinforcement learning method that estimates action values of real state by using triangular-type action distribution model and relationship with its neighboring state which was defined and learned before. This paper proposes a new Region-based Q-learning which uses a reward assigned only when the agent reached the target, and get out of the Local optimal path with adjustment of random action rate. If this is applied to mobile robot navigation, less memory can be used and robot can move smoothly, and optimal solution can be learned fast. To show the validity of our method, computer simulations are illusrated.

• 제어로봇시스템학회논문지
• /
• 제9권7호
• /
• pp.527-535
• /
• 2003

A behavior-based control and learning architecture is proposed, where reinforcement learning is applied to learn proper associations between stimulus and response by using two types of memory called as short Term Memory and Long Term Memory. In particular, to solve delayed-reward problem, a knowledge-propagation (KP) method is proposed, where well-designed or well-trained S-R(stimulus-response) associations for low-level sensors are utilized to learn new S-R associations for high-level sensors, in case that those S-R associations require the same objective such as obstacle avoidance. To show the validity of our proposed KP method, comparative experiments are performed for the cases that (ⅰ) only a delayed reward is used, (ⅱ) some of S-R pairs are preprogrammed, (ⅲ) immediate reward is possible, and (ⅳ) the proposed KP method is applied.

• International journal of advanced smart convergence
• /
• 제6권1호
• /
• pp.39-43
• /
• 2017

As the industry grows, the amount of data grows exponentially, and data analysis using these serves as a predictable solution. As data size increases and processing speed increases, it has begun to be applied to new fields by combining artificial intelligence technology as well as simple big data analysis. In this paper, we propose a method to quickly apply a machine learning based algorithm through efficient resource allocation. The proposed algorithm allocates memory for each attribute. Learning Distinct of Attribute and allocating the right memory. In order to compare the performance of the proposed algorithm, we compared it with the existing K-means algorithm. As a result of measuring the execution time, the speed was improved.

• 전기전자학회논문지
• /
• 제12권1호
• /
• pp.65-74
• /
• 2008

패턴 분류에 많이 사용되는 기법 중의 하나인 메모리 기반 추론 알고리즘은 단순히 메모리에 저장하고 분류 시에 저장된 패턴과 테스트 패턴간의 거리를 계산하여 가장 가까운 학습패턴의 클래스로 분류하는 기법이기 때문에 패턴의 개수가 늘어나면 메모리가 증가하고 또한 추가로 패턴이 발생할 경우 처음부터 다시 수행해야하는 문제점을 가지고 있다. 이러한 문제점을 해결하기 위하여 이미 학습한 대표패턴을 기억하고 새로 들어오는 패턴에 대해서만 학습하는 점진적 학습 방법을 제안한다. 즉 추가로 학습패턴이 발생할 경우 매번 전체 학습 패턴을 다시 학습하는 것이 아니라, 새로 추가된 데이터만을 학습하여 대표패턴을 추출하여 메모리사용을 줄이는 iMPA(incremental Multi Partition Averaging)기법을 제안하였다. 본 논문에서 제안한 기법은 대표적인 메모리기반 추론 기법인 k-NN 기법과 비교하여 현저하게 줄어든 대표패턴으로 유사한 분류 성능을 보여주며, 점진적 특성을 지닌 NGE 이론을 구현한 EACH 시스템과 점진적인 실험에서도 탁월한 분류 성능을 보여준다.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2022년도 추계학술대회
• /
• pp.409-410
• /
• 2022

본 논문은 LSTM(Long-Short Term Memory) 네트워크와 CNN 딥러닝 기법을 기반으로 하는 융합 모델을 제안하고 다중 카테고리 뉴스 데이터 세트에 적용하여 좋은 결과를 얻었다. 실험에 따르면 딥 러닝 기반의 융합 모델이 텍스트 감정 분류의 정밀도와 정확도를 크게 향상시켰다. 이 방법은 모델을 최적화하고 모델의 성능을 향상시키는 중요한 방법이 될 것이다.

• 한국멀티미디어학회논문지
• /
• 제10권11호
• /
• pp.1516-1522
• /
• 2007

FPA(Fixed Partition Averaging) 기법은 기억공간의 효율적인 사용과 분류성능의 향상을 위하여 제안되었던 메모리 기반 추론 기법으로 대상 패턴 공간을 분할 한 후 대표 패턴을 추출하여 분류 기준 패턴으로 사용한다. 이 기법은 메모리 사용 효율과 분류 성능 면에서 우수한 결과를 보인다. 그러나 여러 클래스가 혼합된 분할패턴공간의 경우에 원래의 패턴들을 그대로 저장하여 메모리와 분류성능에 부담으로 작용하는 문제점을 가지고 있다. 본 논문에서는 여러 클래스가 혼합된 분할공간에서 패턴비율을 고려하여 고정분할을 반복적으로 실행하여 초월평면을 생성하고 분류하는 반복적 고정분할평균기법을 제안한다. 본 논문에서 제안한 기법은 기존의 k-NN 기법과 비교하여 현저하게 줄어든 대표패턴을 이용하여 유사한 분류 성능을 보여주며, NGE 이론을 구현한 EACH 시스템과 FPA 기법 등과 비교하여 탁월한 분류 성능을 보여준다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제14권11호
• /
• pp.4246-4267
• /
• 2020

As the network goes deep into all aspects of people's lives, the number and the complexity of network traffic is increasing, and traffic classification becomes more and more important. How to classify them effectively is an important prerequisite for network management and planning, and ensuring network security. With the continuous development of deep learning, more and more traffic classification begins to use it as the main method, which achieves better results than traditional classification methods. In this paper, we provide a comprehensive review of network traffic classification based on deep learning. Firstly, we introduce the research background and progress of network traffic classification. Then, we summarize and compare traffic classification based on deep learning such as stack autoencoder, one-dimensional convolution neural network, two-dimensional convolution neural network, three-dimensional convolution neural network, long short-term memory network and Deep Belief Networks. In addition, we compare traffic classification based on deep learning with other methods such as based on port number, deep packets detection and machine learning. Finally, the future research directions of network traffic classification based on deep learning are prospected.

• 한국컴퓨터정보학회논문지
• /
• 제14권3호
• /
• pp.139-147
• /
• 2009

메모리 기반 추론 기법은 단순히 학습패턴이나 대표패턴의 형태로 메모리에 저장하며 테스트 패턴과의 거리 계산을 통하여 분류한다. 이 기법의 가장 큰 문제점은 학습 패턴 전체를 메모리에 저장하거나 학습 패턴들을 대표 패턴으로 대체하는 방법을 사용함으로 다른 기계학습 방법에 비하여 많은 메모리 공간을 필요로 하며, 저장되는 학습패턴이 증가할수록 분류에 필요한 시간도 많이 소요된다는 단점을 갖는다. 본 논문은 효율적인 메모리 사용과 분류 성능의 향상을 위한 EAS 기법을 제안하였다. 즉, 학습패턴에 대해 분할공간을 생성한 후 생성된 각 분할공간을 MDL기법과 PM기법으로 평가하였다. 그리고 평가 결과 가장 우수한 분할공간만을 취하여 대표패턴으로 삼고 나머지는 다시 분할하여 평가를 반복하는 기법이다. UCI Machine Learning Repository에서 벤치마크 데이터를 발췌한 실험 자료를 사용하여 제안한 기법의 성능과 메모리 사용량에 있어 우수함을 입증하였다.

• 한국환경교육학회지:환경교육
• /
• 제21권4호
• /
• pp.94-110
• /
• 2008

Recently environmental problem becomes such a big issue all over the world that the necessity and importance of the environmental education in school has been simultaneously emphasized. While diverse methods for the environmental education have been researched, this paper, especially focused on a teaching-learning model called GBS (Goal-based scenario), aims to provide a new learner-centered approach for the environmental education. For this purpose, this paper first briefly presents two theoretical backgrounds of GBS (i.e., constructivism and Schank's dynamic memory theory), which is followed by specific and concrete strategies and methods of how to apply GBS in class for the teacher. GBS(Goal-Based Scenario) is a learner-centered model in which learners are presented with a reality-based scenario (or task or problem) and go through several stages of 'missions' to get to a final solution of the given scenario. GBS, while completely resonant with other constructivist learning models in terms of learner-centered approaches, is distinctive from others, when it supplies more specific, structured guides of learning, called 'missions', to the students throughout the whole learning process. In a words, GBS ought to be recognized as an unique learner-centered model compromising the contradictory concepts of 'learner control' and 'structure and specifics' in learning environments still without any damage of constructivist learning principles.