• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.8
• /
• pp.331-338
• /
• 2022

Successor representation (SR) is a model of human reinforcement learning (RL) mimicking the underlying mechanism of hippocampal cells constructing cognitive maps. SR utilizes these learned features to adaptively respond to the frequent reward changes. In this paper, we evaluated the performance of SR under the context where changes in latent variables of environments trigger the reward structure changes. For a benchmark test, we adopted SR-Dyna, an integration of SR into goal-driven Dyna RL algorithm in the 2-stage Markov Decision Task (MDT) in which we can intentionally manipulate the latent variables - state transition uncertainty and goal-condition. To precisely investigate the characteristics of SR, we conducted the experiments while controlling each latent variable that affects the changes in reward structure. Evaluation results showed that SR-Dyna could learn to respond to the reward changes in relation to the changes in latent variables, but could not learn rapidly in that situation. This brings about the necessity to build more robust RL models that can rapidly learn to respond to the frequent changes in the environment in which latent variables and reward structure change at the same time.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.5
• /
• pp.755-762
• /
• 2022

This paper propose a clustered algorithm that possible more efficient COVID-19 disease learning prediction within clustering using context-aware attribute information. In typically, clustering of COVID-19 diseases provides to classify interrelationships within disease cluster information in the clustering process. The clustering data will be as a degrade factor if new or newly processing information during treated as contaminated factors in comparative interrelationships information. In this paper, we have shown the solving the problems and developed a clustering algorithm that can extracting disease correlation information in using K-means algorithm. According to their attributes from disease clusters using accumulated information and interrelationships clustering, the proposed algorithm analyzes the disease correlation clustering possible and centering points. The proposed algorithm showed improved adaptability to prediction accuracy of the classification management system in terms of learning as a group of multiple disease attribute information of COVID-19 through the applied simulation results.

• Journal of the Korea Society of Computer and Information
• /
• v.10 no.5 s.37
• /
• pp.77-86
• /
• 2005

In this paper, we designed a learning algorithm of LVQ that extracts classification errors and learns ones and improves classification performance. The proposed LVQ learning algorithm is the learning Networks which is use SOM to learn initial reference vectors and out-star learning algorithm to determine the class of the output neurons of LVQ. To extract pattern vectors which cause classification errors, we proposed the error-cause condition, which uses that condition and constructed the pattern vector space which consists of the input pattern vectors that cause the classification errors and learned these pattern vectors , and improved performance of the pattern classification. To prove the performance of the proposed learning algorithm, the simulation is performed by using training vectors and test vectors that are Fisher' Iris data and EMG data, and classification performance of the proposed learning method is compared with ones of the conventional LVQ, and it was a confirmation that the proposed learning method is more successful classification than the conventional classification.

• Journal of The Korean Association of Information Education
• /
• v.11 no.3
• /
• pp.267-279
• /
• 2007

The purpose of this study is to design and practice teaching and learning method for routing algorithm among computer science principle which is difficult to be taught to elementary school students and understood by students. And we find out whether elementary school students can understand those learning contents. Intellectual area was assessed through equivalent test paper before and after the test and emotional area was assessed through students' impressions after class. The test showed that routing algorithm could be taught to children. Therefore, this study presents the learnability of routing algorithm as a learning element of elementary school computer education.

• ICROS
• /
• v.1 no.3
• /
• pp.52-61
• /
• 1995

본 고에서는 진화계산의 동작 원리와 이론적 기반에 대해 살펴봄으로써 그 원리를 이해하고 앞으로의 응용가능성에 대하여 고찰하고자 한다. 이를 위해 먼저 대부분의 진화 알고리즘에 공통되는 기본 구성 요소와 계산절차를 기술하고, 진화 알고리즘을 이용하여 특정문제를 풀고자 할 때 고려할 사항에 대하여 기술한다. 다음에는 간단한 응용 문제를 예로 들어 이 문제에 진화 알고리즘을 적용하고 그 동작과정을 추적함으로써 실제 적용에 있어서의 여러 가지 결정사항과 그 수행과정을 구체적으로 살펴본다. 또한 진화 알고리즘의 이론적 배경을 이해하기 위해 스키마와 빌딩 블록 그리고 스키마 정리에 대해서 알아본다. 마지막으로 진화계산방식과 다른 지능적 계산 기술들과의 융합 가능성의 예로서, 유전 프로그래밍에 의한 신경망 구조의 설계 및 학습에 대하여 살펴본다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2000.04b
• /
• pp.256-258
• /
• 2000

최근 들어, 여러 기계학습 알고리즘이 문서 분류와 여과에 사용되고 있다. 특히 AdaBoost와 같은 부스팅 알고리즘은 실세계의 문서 데이터에 사용되었을 때 비교적 좋은 성능을 보이는 것으로 알려져 있다. 그러나 지금까지의 부스팅 알고리즘은 모두 단어의 존재 여부만을 가지고 판단하는 분류자를 기반으로 하고 있기 때문에 가중치 정보를 충분히 사용할 수 없다는 단점이 있다. 이 논문에서는 나이브 베이스를 사용한 부스팅 알고리즘은 단어의 가중치 정보를 효율적으로 사용할 수 있을 뿐 아니라. 확률적으로도 의미있는 신뢰도(confidence ratio)를 생성 할 수 있기 때문이다. TREC-7과 TREC-8의 정보 여과 트랙(filtering track)에 대해서 실험한 결과 좋은 성능을 보여주었다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2006.11a
• /
• pp.39-42
• /
• 2006

본 논문에서는 데이터 마이닝에서 발생되는 희귀 데이터를 분석하기 위한 희귀 목적값 분석의 새로운 알고리즘을 제시한다. 이를 위하여 속성들이 가지는 속성의 가중치 값과 속성값이 목적 속성에 미치는 가중치값을 정보이론에 입각하여 가중치 계산을 하고, 계산된 가중치값을 사용하여 스코어링 함으로써 희귀 목적값에 속한 데이터 예측/분류에 사용하는 방법을 제시하였다. 실험을 통해 본 알고리즘의 성능을 입증함은 물론 제안된 알고리즘이 희귀 데이터의 분류/학습에 좀 더 효과적이다는 것을 보였다.

• Proceedings of the Korea Multimedia Society Conference
• /
• 2002.05c
• /
• pp.320-324
• /
• 2002

본 연구에서는 모멘트와 뉴우턴법 및 모멘트와 할선법에 각각 기초한 고정점 알고리즘의 신경망 기반 독립성분분석 기법을 제안하였다. 여기서 뉴우턴법과 할선법은 각각 엔트로피에 기초한 목적함수의 근을 구하는 근사화 방법으로 빠른 경신을 위함이고, 모멘트는 근사화에 의한 역혼합행렬의 경신과정에서 발생하는 발진을 줄여 좀 더 빠른 학습을 위함이다. 제안된 기법을 256×256 픽셀(pixel)의 8개 지문영상으로부터 임의의 혼합행렬에 따라 발생되는 영상들을 각각 대상으로 시뮬레이션 한 결과, 모멘트와 할선법에 기초한 알고리즘이 모멘트와 뉴우턴에 기초한 알고리즘보다 우수한 분리성능과 빠른 학습속도가 있음을 확인하였다.

• The Korean Journal of Applied Statistics
• /
• v.26 no.5
• /
• pp.847-856
• /
• 2013

We propose a modified learning process for generalized neural network using a learning algorithm by Liu et al. (2001). We consider the effect of initial weights, training results and learning errors using a modified learning process. We employ an incremental training procedure where training patterns are learned systematically. Our algorithm starts with a single training pattern and a single hidden layer neuron. During the course of neural network training, we try to escape from the local minimum by using a weight scaling technique. We allow the network to grow by adding a hidden layer neuron only after several consecutive failed attempts to escape from a local minimum. Our optimization procedure tends to make the network reach the error tolerance with no or little training after the addition of a hidden layer neuron. Simulation results with suitable initial weights indicate that the present constructive algorithm can obtain neural networks very close to minimal structures and that convergence to a solution in neural network training can be guaranteed. We tested these algorithms extensively with small training sets.

• The Journal of Information Technology
• /
• v.4 no.1
• /
• pp.71-79
• /
• 2001

This paper presents an adaptive back propagation algorithm that update the learning parameter by the generated error, adaptively and configuration of the range for the initial connecting weight according to the different maximum target value from minimum target value. This algorithm is expected to escaping from the local minimum and make the best environment for the convergence. On the simulation tested this algorithm on three learning pattern. The first was 3-parity problem learning, the second was $7{\times}5$ dot alphabetic font learning and the third was handwritten primitive strokes learning. In three examples, the probability of becoming trapped in local minimum was reduce. Furthermore, in the alphabetic font and handwritten primitive strokes learning, the neural network enhanced to loaming efficient about 27%~57.2% for the standard back propagation(SBP).