Training principles for unsupervised learning are often derived from motivations that appear to be independent of supervised learning. In this paper we present a simple unificatio...
The use of domain knowledge in a learner can greatly improve the models it produces. However, high-quality expert knowledge is very difficult to obtain. Traditionally, researchers...
We report a method for semi-automated segmentation of extended features such as filamentous structures in electron tomograms. We present an application of this method for the auto...
Sriram Subramaniam, Peijun Zhang, David Germain, T...
This paper presents a semi-automatic method for the segmentation and the tracking of the mitral valve leaflet in transesophageal echocardiography. We use two connected active cont...
Traditional static type systems are very effective for verifying basic interface specifications, but are somewhat limited in the kinds specificationsthey support. Dynamically-chec...