This conference Proceedings contains 58 papers presented in 8 sessions dealing with: vision and robotics problems needing solutions;pattern recognition for computervision;image processing;intelligent materials handli...
详细信息
This conference Proceedings contains 58 papers presented in 8 sessions dealing with: vision and robotics problems needing solutions;pattern recognition for computervision;image processing;intelligent materials handling and vision;novel preprocessing algorithms and hardware;technology to support intelligentrobots and automated systems;fuzzy logic in intelligent systems and computervision;image segmentation techniques. The topics considered include the following, among others: learning procedure for the recognition of 3-D objects from 2-D images;flexible gray-level vision system based on multiple cell feature description and Hough transform;extraction of the foveal center and lesion boundary from fundus images;design and characterization of a space-variant CCD sensor;toward a general formula for analogical learning leading to more autonomous systems;image analysis using attributed fuzzy tournament matching algorithm;fuzzy logic for fault diagnosis;color segmentation using minimum description length (MDL) clustering;segmentation using range data and structured light;finding distinctive colored regions in images;multiresolution segmentation of forward-looking IP and SAR imagery using neural networks.
The authors ask what is the complexity of computing equilibria for physically realizable analog networks like those of J.J. Hopfield (1984) and T.J. Sejnowski (1981) with arbitrary connectivity. It is shown that, if t...
详细信息
The authors ask what is the complexity of computing equilibria for physically realizable analog networks like those of J.J. Hopfield (1984) and T.J. Sejnowski (1981) with arbitrary connectivity. It is shown that, if the amplifiers are piecewise-linear, then such networks are instances of a game-theoretic model known as polymatrix games. Equilibria for the latter may be computed by vertex pivoting algorithms similar to the simplex method for linear programming, which are in practice of low order polynomial complexity. These algorithms appear to be the only ones both guaranteed to work and which are polynomial in practice. These results suggest that networks with few nonstable equilibria would be computationally attractive.< >
暂无评论