Sciweavers

1377 search results - page 56 / 276
» Neural Computing
Sort
View
IPPS
1998
IEEE
13 years 12 months ago
Using the BSP Cost Model to Optimise Parallel Neural Network Training
We derive cost formulae for three di erent parallelisation techniques for training supervised networks. These formulae are parameterised by properties of the target computer archit...
R. O. Rogers, David B. Skillicorn
IWANN
2001
Springer
14 years 5 days ago
Landmark Recognition for Autonomous Navigation Using Odometric Information and a Network of Perceptrons
In this paper two methods for the detection and recognition of landmarks to be used in topological modeling for autonomous mobile robots are presented. The first method is based o...
Javier de Lope Asiaín, Darío Maraval...
ISCAS
2007
IEEE
122views Hardware» more  ISCAS 2007»
14 years 2 months ago
Neuromimetic ICs with analog cores: an alternative for simulating spiking neural networks
- This paper aims at discussing the implementation of simulation systems for SNN based on analog computation cores (neuromimetic ICs). Such systems are an alternative to completely...
Sylvie Renaud, Jean Tomas, Yannick Bornat, Adel Da...
IJCNN
2006
IEEE
14 years 1 months ago
Job-Shop Scheduling with an Adaptive Neural Network and Local Search Hybrid Approach
— Job-shop scheduling is one of the most difficult production scheduling problems in industry. This paper proposes an adaptive neural network and local search hybrid approach fo...
Shengxiang Yang
IJCNN
2000
IEEE
14 years 3 days ago
A Neural Support Vector Network Architecture with Adaptive Kernels
In the Support Vector Machines (SVM) framework, the positive-definite kernel can be seen as representing a fixed similarity measure between two patterns, and a discriminant func...
Pascal Vincent, Yoshua Bengio