Sciweavers

602 search results - page 106 / 121
» A New Approximation Method of the Quadratic Discriminant Fun...
Sort
View
STOC
1993
ACM
141views Algorithms» more  STOC 1993»
15 years 1 months ago
Bounds for the computational power and learning complexity of analog neural nets
Abstract. It is shown that high-order feedforward neural nets of constant depth with piecewisepolynomial activation functions and arbitrary real weights can be simulated for Boolea...
Wolfgang Maass
ICPR
2002
IEEE
15 years 10 months ago
Self-Calibration and Neural Network Implementation of Photometric Stereo
This paper describes a new approach to neural network implementation of photometric stereo for a rotational object with non-uniform reflectance factor. Three input images are acqu...
Yuji Iwahori, Yumi Watanabe, Robert J. Woodham, Ak...
CP
2009
Springer
15 years 4 months ago
Reasoning about Optimal Collections of Solutions
The problem of finding a collection of solutions to a combinatorial problem that is optimal in terms of an inter-solution objective function exists in many application settings. F...
Tarik Hadzic, Alan Holland, Barry O'Sullivan
ICNP
2003
IEEE
15 years 2 months ago
Power Adaptive Broadcasting with Local Information in Ad Hoc Networks
Network wide broadcasting is an energy intensive function. In this paper we propose a new method that performs transmission power adaptations based on information available locall...
Xiaohu Chen, Michalis Faloutsos, Srikanth V. Krish...
GLVLSI
2009
IEEE
146views VLSI» more  GLVLSI 2009»
15 years 1 months ago
A reconfigurable stochastic architecture for highly reliable computing
Mounting concerns over variability, defects and noise motivate a new approach for integrated circuits: the design of stochastic logic, that is to say, digital circuitry that opera...
Xin Li, Weikang Qian, Marc D. Riedel, Kia Bazargan...