This work investigates the use of nonlinear dependencies in natural image sequence statistics to learn higher-order structures in natural videos. We propose a two-layer model that...
A critical path in the development of natural language understanding NLU modules lies in the di culty of de ning a mapping from words to semantics: Usually it takes in the order o...
The purpose of extractive summarization is to automatically select a number of indicative sentences, passages, or paragraphs from the original document according to a target summa...
The control of robot swarming in a distributed manner is a difficult problem because global behaviors must emerge as a result of many local actions. This paper uses a bio-inspired ...
Wei-Min Shen, Peter M. Will, Aram Galstyan, Cheng-...
Spoken language is one of the most intuitive forms of interaction between humans and agents. Unfortunately, agents that interact with people using natural language often experienc...