Within the last gears various principal component analysis (PCA) algorithms have been proposed. In this paper me use a general framework to describe those PCA algorithms which are based on Hebbian learning. For an imp...
详细信息
Within the last gears various principal component analysis (PCA) algorithms have been proposed. In this paper me use a general framework to describe those PCA algorithms which are based on Hebbian learning. For an important subset of these algorithms, the local algorithms, me fully describe their equilibria, where all lateral connections are set to zero and their local stability. We show how the parameters in the PCA algorithms have to be chosen in order to get an algorithm which converges to a stable equilibrium which pro tides principal component extraction.
On serial computers, global segmentation methods are preferred to local methods due to their lower CPU time requirements. However, due to the increased availability of parallel machines, if local segmentation algorith...
详细信息
On serial computers, global segmentation methods are preferred to local methods due to their lower CPU time requirements. However, due to the increased availability of parallel machines, if local segmentation algorithms are efficiently parallelizable then they are also equally preferable. In this letter, we have implemented some widely used image thresholding algorithms on a Connection Machine-200 to know their parallel complexity. Compared to global methods, local methods are observed to be efficiently parallelizable.
This paper presents SuperSAB: an adaptive acceleration strategy for error back propagation learning. The strategy is compared with the original back propagation algorithm, as well as with previously proposed accelerat...
详细信息
This paper presents SuperSAB: an adaptive acceleration strategy for error back propagation learning. The strategy is compared with the original back propagation algorithm, as well as with previously proposed acceleration techniques. It will be shown that SuperSAB may converge orders of magnitude faster than the original back propagation algorithm, and is only slightly instable. In addition, the algorithm is very insensitive to the choice of parameter values, and has excellent scaling properties. All simulations have been carried out on the Edinburgh concurrent supercomputer: a large parallel computer system, based on transputers. The power of this machine made it possible to test both SuperSAB and the original back propagation algorithm very extensively. As a result, this paper presents some interesting phenomenology results on the influence of parameter values in the original back propagation algorithm.
暂无评论