- Full text PDF available (8)
- This year (0)
- Last 5 years (0)
- Last 10 years (3)
Journals and Conferences
A recently published idea is to use the A*-Algorithm to optimize the topology of Neural Networks. In this paper, optimization techniques are investigated that combine the A*-Algorithm with diierent parallel training algorithms, namely the backpropagation algorithm and several hybrid algorithms. The hybrid algorithms combine the backpropagation's steepest… (More)
Algorithms for learning and optimization of Neural Networks and Genetic Algorithms often have a very high demand on computational power. Connecting distributed computers to a powerful metacomputer via a network, suucient power can be achieved. To create distributed systems, middleware tools are needed for the modelling of distributed programs, transfer of… (More)
This paper presents a methodology that is used to detect predeened algorithmic structures (skeletons) in a ne granular program speciication. For each skeleton the best mapping on a particular massively parallel system is known. The skeleton identiication process helps in making good mapping decisions.