• 전기학회논문지
• /
• 제64권1호
• /
• pp.113-120
• /
• 2015

In this paper, we propose a feature extraction method using the stacked autoencoders which consist of restricted Boltzmann machines. The stacked autoencoders is a sort of deep networks. Restricted Boltzmann machines (RBMs) are probabilistic graphical models that can be interpreted as stochastic neural networks. In terms of pattern classification problem, the feature extraction is a key issue. We use the stacked autoencoders networks to extract new features which have a good influence on the improvement of the classification performance. After feature extraction, fuzzy k-nearest neighbors algorithm is used for a classifier which classifies the new extracted data set. To evaluate the classification ability of the proposed pattern classifier, we make some experiments with several machine learning data sets.

• 한국멀티미디어학회논문지
• /
• 제23권1호
• /
• pp.1-7
• /
• 2020

Clustering methods essentially take a two-step approach; extracting feature vectors for dimensionality reduction and then employing clustering algorithm on the extracted feature vectors. However, for clustering images, the traditional clustering methods such as stacked auto-encoder based k-means are not effective since they tend to ignore the local information. In this paper, we propose a method first to effectively reduce data dimensionality using convolutional auto-encoder to capture and reflect the local information and then to accurately cluster similar data samples by using a hierarchical clustering approach. The experimental results confirm that the clustering results are improved by using the proposed model in terms of clustering accuracy and normalized mutual information.

• 인터넷정보학회논문지
• /
• 제18권6호
• /
• pp.25-34
• /
• 2017

오토인코더(Autoencoder)는 입력 계층과 출력 계층이 동일한 딥러닝의 일종으로 은닉 계층의 제약 조건을 이용하여 입력 벡터의 특징을 효과적으로 추출하고 복원한다. 본 논문에서는 CAPTCHA 이미지 중 하나의 숫자와 자연배경이 혼재된 영역을 대상으로 일련의 다양한 오토인코더 모델들을 적용하여 잡음인 자연배경을 제거하고 숫자 이미지만을 복원하는 방법들을 제시한다. 제시하는 복원 이미지의 적합성은 오토인코더의 출력을 입력으로 하는 소프트맥스 함수를 활성화 함수로 사용하여 검증하고, CAPTCHA 정보를 자동으로 획득하는 다른 방법들과 비교하여, 본 논문에서 제시하는 방법의 우수함을 검증하였다.