Year: 2019
Type: dissertation
Abstract: In this thesis, we propose two learning methodologies for deep learning models. \nWe consider two cases: semi-supervised learning and unsupervised learning. \n \nIn semi-supervised learning, we spell out a new semi-supervised learning method, called GAB, that searches for a decision boundary whose neighborhood overlaps the least with the support of unlabeled data. \nWe construct a formal measure of the degree of overlap between the neighborhood of a given decision boundary and the support of unlabeled data and develop an algorithm to learn the model, which minimizes this penalty term. We theoretically prove that GAB finds the Bayes classifier successively and devise an algorithm with an approximated penalty term by generating artificial data near the current decision boundary based on an adversarial training technique. We empirically show that GAB not only competes well with the recent studies in prediction power but also requires much smaller computational resources. \n \nIn unsupervised learning, we propose a method for generative models maximizing the log-likelihood of observable variables directly by using the EM algorithm and an importance sampling algorithm, instead of employing variational inference. A novel feature of the proposed method is to develop a warm start technique by taking a convex combination of the expected complete log-likelihood and variational lower bound in the E-step, which stabilizes the learning procedure and thus results in superior performance. The proposed learning method called VAEM outperforms other variational methods in terms of the test log-likelihood without increasing computational cost much, generates more sharp and realistic images, and can be easily modified for nonstandard cases such as the presence of missing data which is not obvious for variational methods.
Author: 김동하
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W3112511915