In this paper we propose a financial trading system whose strategy is developed by means of an artificial neural network approach based on a recurrent reinforcement learning algo...
This article describes a new segmentation by thresholding approach based on learning. The method consists in learning to threshold correctly submitting both an image and its ideal...
- Peer-to-peer (P2P) offers good solutions for many applications such as large data sharing and collaboration. Thus, it appears as a powerful paradigm to develop scalable distribut...
Stainam N. Brandao, Ricardo T. Silva, Jano M. Souz...
Although speech and language processing techniques achieved a relative maturity during the last decade, designing a spoken dialogue system is still a tailoring task because of the ...
This paper addresses the interaction between randomization, with restart strategies, and learning, an often crucial technique for proving unsatisfiability. We use instances of SAT ...