Semi-supervised learning, which uses unlabeled data to help learn a discriminative model, is especially important for structured output problems, as considerably more effort is needed to label its multi-dimensional outputs versus standard single output problems. We propose a new max-margin framework for semi-supervised structured output learning, that allows the use of powerful discrete optimiz...

This paper presents a novel semisupervised learning algorithm called Active Deep Networks (ADN), to address the semi-supervised sentiment classification problem with active learning. First, we propose the semi-supervised learning method of ADN. ADN is constructed by Restricted Boltzmann Machines (RBM) with unsupervised learning using labeled data and abundant of unlabeled data. Then the constru...

In this thesis, a study on gene expression data analysis is done using some supervised, unsupervised and semi-supervised approaches. The task of class prediction for six gene expression datasets (namely, Brain Tumor, Colon Cancer, Leukemia, Lymphoma and SRBCT) has been carried out. Here, a one-dimensional self-organizing feature maps (SOFM) in a semi-supervised learning framework is developed f...

We propose a novel and flexible approach to meta-learning for learning-to-learn from only a few examples. Our framework is motivated by actor-critic reinforcement learning, but can be applied to both reinforcement and supervised learning. The key idea is to learn a meta-critic: an action-value function neural network that learns to criticise any actor trying to solve any specified task. For sup...

Semi-supervised learning algorithms reduce the high cost of acquiring labeled training data by using both labeled and unlabeled data during learning. Deep Convolutional Networks (DCNs) have achieved great success in supervised tasks and as such have been widely employed in the semi-supervised learning. In this paper we leverage the recently developed Deep Rendering Mixture Model (DRMM), a proba...

of thesis entitled: Statistical Machine Learning for Bridging the Semantic Gap in Image Retrieval Submitted by HOI, Chu Hong (Steven) With the explosive growth of multimedia data, more and more research attentions have been devoted to visual information retrieval. Image retrieval, particularly content-based image retrieval (CBIR), has been actively studied in multimedia information retrieval co...

We consider the problem of learning a distance metric from a limited amount of pairwise information as effectively as possible. The proposed SERAPH (SEmi-supervised metRic leArning Paradigm with Hyper sparsity) is a direct and substantially more natural approach for semi-supervised metric learning, since the supervised and unsupervised parts are based on a unified information theoretic framewor...

Semi-supervised clustering employs a small amount of labeled data to aid unsupervised learning. The focus of this paper is on Metric Learning, with particular interest in incorporating side information to make it semi-supervised. This study is primarily motivated by an application: face-image clustering. In the paper introduces metric learning and semi-supervised clustering, Similarity metric l...