• Journal of Electrical Engineering and Technology
• /
• 제13권5호
• /
• pp.2099-2106
• /
• 2018

This study presents a novel approach of discriminative feature vectors based on manifold learning using nonlinear dimension reduction (DR) technique to improve loss function, and combine with the Adversarial examples to regularize the object function for image classification. The traditional convolutional neural networks (CNN) with many new regularization approach has been successfully used for image classification tasks, and it achieved good results, hence it costs a lot of Calculated spacing and timing. Significantly, distrinct from traditional CNN, we discriminate the feature vectors for objects without empirically-tuned parameter, these Discriminative features intend to remain the lower-dimensional relationship corresponding high-dimension manifold after projecting the image feature vectors from high-dimension to lower-dimension, and we optimize the constrains of the preserving local features based on manifold, which narrow the mapped feature information from the same class and push different class away. Using Adversarial examples, improved loss function with additional regularization term intends to boost the Robustness and generalization of neural network. experimental results indicate that the approach based on discriminative feature of manifold learning is not only valid, but also more efficient in image classification tasks. Furthermore, the proposed approach achieves competitive classification performances for three benchmark datasets : MNIST, CIFAR-10, SVHN.

• Journal of the Korean Data and Information Science Society
• /
• 제21권3호
• /
• pp.461-470
• /
• 2010

라벨 있는 자료가 분류규칙을 만들 만큼 충분하지 않거나, 라벨 없는 자료가 분류규칙을 만드는데 도움을 줄 수 있는 경우에는 라벨 있는 자료와 라벨 없는 자료를 모두 사용하는 준지도분류가 더 효과적이다. 준지도분류 중 그래프기반 다양체정칙법이 개발되어 최근에 많은 연구가 이루어지고 있다. 본 연구에서는 통계적학습에서 좋은 성능을 보이는 최소제곱 서포터벡터기계를 준지도분류에 적용시키는 방법을 제안한다. 모의실험을 통해 제안된 방법이 라벨 없는 자료를 잘 활용하는 것을 볼 수 있었다.

• Journal of the Korean Data and Information Science Society
• /
• 제22권1호
• /
• pp.99-105
• /
• 2011

We propose a semi-supervised learning algorithm based on a form of regularization that incorporates similarity and dissimilarity penalty terms. Our approach uses a graph-based encoding of similarity and dissimilarity. We also present a model-selection method which employs cross-validation techniques to choose hyperparameters which affect the performance of the proposed method. Simulations using two types of dat sets demonstrate that the proposed method is promising.