Mass digitization of historical documents is a challenging problem for optical character recognition (OCR) tools. Issues include noisy backgrounds and faded text due to aging, bor...
Anshul Gupta, Ricardo Gutierrez-Osuna, Matthew Chr...
Data-driven analytics—in areas ranging from consumer marketing to public policy—often allow behavior prediction at the level of individuals rather than population segments, of...
Tractable classes constitute an important issue in Artificial Intelligence to define new islands of tractability for reasoning or problem solving. In the area of constraint netw...
Modern society is critically dependent on the services provided by engineered infrastructure networks. When natural disasters (e.g. Hurricane Sandy) occur, the ability of these ne...
A fundamental task in reasoning about action and change is projection, which refers to determining what holds after a number of actions have occurred. A powerful method for solvin...
As Machine Learning (ML) applications embrace greater data size and model complexity, practitioners turn to distributed clusters to satisfy the increased computational and memory ...
Recently, action language BC, which combines the attractive features of action languages B and C+, was proposed. While BC allows Prolog-style recursive definitions that are not av...
In human-robot dialogue, although a robot and its human partner are co-present in a shared environment, they have significantly mismatched perceptual capabilities (e.g., recogniz...
Compositional semantic aims at constructing the meaning of phrases or sentences according to the compositionality of word meanings. In this paper, we propose to synchronously lear...
An important problem in analyzing complex networks is discovery of modular or community structures embedded in the networks. Although being promising for identifying network commu...