The chaotic Boltzmann machine proposed in this paper is a chaotic pseudo-billiard system that works as a Boltzmann machine. Chaotic Boltzmann machines are shown numerically to have computing abilities comparable to conventional (stochastic) Boltzmann machines. Since no randomness is required, efficient hardware implementation is expected. Moreover, the ferromagnetic phase transition of the Isin...

Many researchers have been developing natural language dialogue systems as a human-friendly man-machine interface. The human factors in a man-machine dialogue, however, are not obvious enough to understand with regard to how people talk with a dialogue system. 141 dialogues which our dialogue system had in DiaLeague '97 were analyzed at the utterance and dialogue levels, where DiaLeague '97 was...

This paper describes a nursing robot system that is called DO-U-MI developed for helping elderly and disabled people. For that purpose, the nursing robot system has a capability to assist elderly and disabled people to move independently in indoor environments such as a nursing home. It also provides a convenient man-machine interface for easy usage and various entertainment services for users....

We investigate the structure of conformal C-spaces, a class of Riemmanian man-ifolds which naturally arises as a conformal generalisation of the Einstein condition. A basic question is when such a structure is closed, or equivalently locally conformally Cotton. In dimension 4 we obtain a full answer to this question and also investigate the incidence of the Bach condition on this class of metri...

Skeem for their thoughtful comments and suggestions.

We present a purely geometrical proof that under the weak perspective model, the 3D pose of a 3-point configuration is determined uniquely up to a reflection by its 2C) projection.

Statistical models almost always yield predictions that are more accurate than those of human experts. However, humans are better at data acquisition and at recognizing atypical circumstances. We use prediction markets to combine predictions from groups of humans and artificialintelligence agents and show that they are more robust than those from groups of humans or agents alone.

We propose a simple, physical model for the studying natural images, use it to derive an analytical density function for real images and compare this function to empirical results. In addition to treating the multi-dimensional case, we propose several extensions of this model.