We present a hierarchical generative model for object recognition that is constructed by weakly-supervised learning. A key component is a novel, adaptive patch feature whose width...
In multi-task learning our goal is to design regression or classification models for each of the tasks and appropriately share information between tasks. A Dirichlet process (DP) ...
By expanding the teaching styles used in computer science classrooms, we can expand the audience of students that enjoy and excel in technology. Rather than focusing on major curr...
Abstract. In this paper we introduce BioPubMiner, a machine learning component-based platform for biomedical information analysis. BioPubMiner employs natural language processing t...
Automatically translating natural language into machine-readable instructions is one of major interesting and challenging tasks in Natural Language (NL) Processing. This problem c...