• Journal of the Korea Society of Computer and Information
• /
• v.15 no.4
• /
• pp.57-63
• /
• 2010

The damping parameter of Levenberg-Marquardt algorithm switches between error backpropagation and Gauss-Newton learning and affects learning speed. Fixing the damping parameter induces some oscillation of error and decreases learning speed. Therefore, we propose the way of a variable damping parameter with referring to the alternation of error. The proposed method makes the damping parameter increase if error rate is large and makes it decrease if error rate is small. This method so plays the role of momentum that it can improve learning speed. We tested both iris recognition and wine recognition for this paper. We found out that this method improved learning speed in 67% cases on iris recognition and in 78% cases on wine recognition. It was also showed that the oscillation of error by the proposed way was less than those of other algorithms.

• Journal of Korea Game Society
• /
• v.17 no.4
• /
• pp.109-116
• /
• 2017

It takes quite amount of time to study a board game because there are many game characters and many state spaces are exist for board games. Therefore, game must do learning long. But, there is weakness with reinforcement learning. On Learning early, the learning speed becomes slow. If there were equal result that both are considered to be best ones during the course of learning stage, Heuristic which utilizes learning of problem area of Jul-Gonu was used to improve the speed of learning. To compare a normal character to an improved one, a board game was created, and then they fought against each other. As a result, improved character's ability was improved on learning speed.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.05a
• /
• pp.530-531
• /
• 2023

딥러닝에서 지식 증류 기법은 큰 모델의 지식을 작은 모델로 전달하여 작은 모델의 성능을 개선하는 방식이다. 지식 증류 기법은 모델 경량화, 학습 속도 향상, 학습 정확도 향상 등에 활용될 수 있는데, 교사 모델이라 불리는 큰 모델은 일반적으로 학습된 딥러닝 모델을 사용한다. 본 연구에서는 학습된 딥러닝 모델 대신에 수치 기반 시뮬레이션 모델을 사용함으로써 어떠한 효과가 있는지 검증하였으며, 수치 모델을 활용한 기상 예측 모델에서의 지식 증류는 기존 단독 딥러닝 모델 학습 대비 더 작은 학습 횟수(epoch)에서도 동일한 에러 수준(RMSE)까지 도달하여, 학습 속도 측면에서 이득이 있음을 확인하였다.

• Journal of Sensor Science and Technology
• /
• v.8 no.1
• /
• pp.45-52
• /
• 1999

In this raper, an enhanced learning method is proposed for improving the learning speed of the error back propagation learning algorithm. In order to cope with the premature saturation phenomenon at the initial learning stage, a variation scheme of active functions is introduced by using higher order functions, which does not need much increase of computation load. It naturally changes the learning rate of inter-connection weights to a large value as the derivative of sigmoid function abnormally decrease to a small value during the learning epoch. Also, we suggest the hybrid learning method incorporated the proposed method with the momentum training algorithm. Computer simulation results show that the proposed learning algorithm outperforms the conventional methods such as momentum and delta-bar-delta algorithms.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2020.05a
• /
• pp.567-569
• /
• 2020

여러 악기가 섞여 있는 음원으로부터 원하는 악기 소리를 추출하는 음원 분리 기법 중 최근 신경망 기반 시스템이 활발히 연구되고 있다. 악기마다 고유의 음역대를 가진다는 사실에 감안하여, 연구진은 기존 음원 분리 신경망에 적은 수의 학습 파라미터를 추가하여 학습 속도를 대폭 향상시킬 수 있는 음역대 강조 기법을 제안한다.

• Journal of Korea Game Society
• /
• v.18 no.4
• /
• pp.99-106
• /
• 2018

Board games have many game characters and many state spaces. Therefore, games must be long learning. This paper used reinforcement learning algorithm. But, there is weakness with reinforcement learning. At the beginning of learning, reinforcement learning has the drawback of slow learning speed. Therefore, we tried to improve the learning speed by using the heuristic using the knowledge of the problem domain considering the game tree when there is the same best value during learning. In order to compare the existing character the improved one. I produced a board game. So I compete with one-sided attacking character. Improved character attacked the opponent's one considering the game tree. As a result of experiment, improved character's capability was improved on learning speed.

• Journal of Internet Computing and Services
• /
• v.11 no.1
• /
• pp.77-84
• /
• 2010

Children, who have a language disorder, have difficulty in expressing their reaction about stimulus of sound and vision. So it is very hard to grasp that they recognize external stimulus or not. For solving these problem, we can check response time and make them to choose stimulus by giving stimulus of sound and vision to them through Audio and Visual Stimulus and Reaction Meter System. Additionally, We can help them by improving response time by repeated study based on the results and making them to recognize and choose stimulus faster without aversion about external stimulus. It would make them not to feel uncomfortable and isolated because they are unfamiliar with external stimulus.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1998.10a
• /
• pp.251-254
• /
• 1998

본 논문에서는 신경회로망의 수렴속도를 높이기 위한 알고리즘을 제안한다. 전형적인 역전파 학습방식은 느린 수렴속도가 단점으로 제기되는데 이는 비용함수의 계곡부근에서 가중치의 궤적이 심한 진동현상을 보이기 때문이다. 이 문제를 해결하기 위해서 본 논문에서는 경사법에서 사용되는 갱신방향을 계곡의 진행방향을 이용하여 변경한다. 모의실험을 통하여 제안된 방법으로 가중치의 궤적에 나타나는 진동을 줄이고 수렴속도를 향상시킬 수 있음을 보인다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2002.04b
• /
• pp.616-618
• /
• 2002

MLP(multilayer perceptron)는 다른 패턴인식 방법에 비해 몇 가지 이점이 있어 다양한 문제영역에서 사용되고 있다 그러나 MLP의 학습에 일반적으로 사용되는 EBP(error backpropagation) 알고리즘은 학습시간이 비교적 오래 걸린다는 단점이 있으며, 이는 실시간 처리를 요구하는 문제나 대규모 데이터 및 MLP 구조로 인해 학습시간이 상당히 긴 문제에서 제약으로 작용한다. 패턴인식에 사용되는 학습데이터는 풍부한 중복특성을 내포하고 있으므로 패턴마다 MLP의 내부변수를 갱신하는 은라인 계열의 학습방식이 속도의 향상에 상당한 효과가 있다. 일반적인 온라인 EBP 알고리즘에서는 내부 가중치 갱신시 고정된 학습률을 적용한다. 고정 학습률을 적절히 선택함으로써 패턴인식 응용에서 상당한 속도개선을 얻을 수 있지만, 학습률을 고정함으로써 온라인 방식에서 패턴별 갱신의 특성을 완전히 활용하지 못하는 비효율성이 발생한다. 또한, 학습도중 패턴군이 학습된 패턴과 그렇지 못한 패턴으로 나뉘고 이 가운데 학습된 패턴은 학습을 위한 계산에 포함될 필요가 없음에도 불구하고, 기존의 온라인 EBP에서는 에폭에 할당된 모든 패턴을 일률적으로 계산에 포함시킨다. 이 문제에 대해 본 논문에서는 학습이 진행됨에 따라 패턴마다 적절한 학습률을 적용하고 필요한 패턴만을 학습에 반영하는 패턴별 가변학습률 및 학습생략(COIL) 방댑을 제안한다. 제안한 COIL의 성능을 입증하기 위해 화자증명과 음성인식을 실험하고 그 결과를 제시한다.

• Journal of Korea Game Society
• /
• v.10 no.1
• /
• pp.105-113
• /
• 2010

It takes quite amount of time to study a board game because there are many game characters and different stages are exist for board games. Also, the opponent is not just a single character that means it is not one on one game, but group vs. group. That is why strategy is needed, and therefore applying optimum learning is a must. If there were equal result that both are considered to be best ones during the course of learning stage, Heuristic which utilizes learning of problem area of Jul-Gonu was used to improve the speed of learning. To compare a normal character to an improved one, a jul-gonu game was created, and then they fought against each other. Improved character considered distance and attacked other one. As a result, improved character's ability was improved on learning speed.