Sciweavers

10828 search results - page 291 / 2166
» Improving the application of process models
Sort
View
NPL
2000
88views more  NPL 2000»
15 years 6 months ago
Learning Synaptic Clusters for Nonlinear Dendritic Processing
Nonlinear dendritic processing appears to be a feature of biological neurons and would also be of use in many applications of artificial neural networks. This paper presents a mod...
Michael W. Spratling, Gillian Hayes
ICASSP
2008
IEEE
16 years 1 months ago
A weighted subspace approach for improving bagging performance
Bagging is an ensemble method that uses random resampling of a dataset to construct models. In classification scenarios, the random resampling procedure in bagging induces some c...
Qu-Tang Cai, Chun-Yi Peng, Chang-Shui Zhang
181
Voted
ICFP
2003
ACM
16 years 6 months ago
Scripting the type inference process
To improve the quality of type error messages in functional programming languages, we propose four techniques which influence the behaviour of constraint-based type inference proc...
Bastiaan Heeren, Jurriaan Hage, S. Doaitse Swierst...
ISCA
2007
IEEE
117views Hardware» more  ISCA 2007»
16 years 1 months ago
ReCycle: : pipeline adaptation to tolerate process variation
Process variation affects processor pipelines by making some stages slower and others faster, therefore exacerbating pipeline unbalance. This reduces the frequency attainable by t...
Abhishek Tiwari, Smruti R. Sarangi, Josep Torrella...
ISVLSI
2006
IEEE
104views VLSI» more  ISVLSI 2006»
16 years 22 days ago
Adaptive Signal Processing in Mixed-Signal VLSI with Anti-Hebbian Learning
We describe analog and mixed-signal primitives for implementing adaptive signal-processing algorithms in VLSI based on anti-Hebbian learning. Both on-chip calibration techniques a...
Miguel Figueroa, Esteban Matamala, Gonzalo Carvaja...