2 resultados para Learning support

em National Center for Biotechnology Information - NCBI


Relevância:

30.00% 30.00%

Publicador:

Resumo:

We introduce a method of functionally classifying genes by using gene expression data from DNA microarray hybridization experiments. The method is based on the theory of support vector machines (SVMs). SVMs are considered a supervised computer learning method because they exploit prior knowledge of gene function to identify unknown genes of similar function from expression data. SVMs avoid several problems associated with unsupervised clustering methods, such as hierarchical clustering and self-organizing maps. SVMs have many mathematical features that make them attractive for gene expression analysis, including their flexibility in choosing a similarity function, sparseness of solution when dealing with large data sets, the ability to handle large feature spaces, and the ability to identify outliers. We test several SVMs that use different similarity metrics, as well as some other supervised learning methods, and find that the SVMs best identify sets of genes with a common function using expression data. Finally, we use SVMs to predict functional roles for uncharacterized yeast ORFs based on their expression data.

Relevância:

30.00% 30.00%

Publicador:

Resumo:

We have determined the volume and location of hippocampal tissue required for normal acquisition of a spatial memory task. Ibotenic acid was used to make bilateral symmetric lesions of 20-100% of hippocampal volume. Even a small transverse block (minislab) of the hippocampus (down to 26% of the total) could support spatial learning in a water maze, provided it was at the septal (dorsal) pole of the hippocampus. Lesions of the septal pole, leaving 60% of the hippocampi intact, caused a learning deficit, although normal electrophysiological responses, synaptic plasticity, and preserved acetylcholinesterase staining argue for adequate function of the remaining tissue. Thus, with an otherwise normal brain, hippocampal-dependent spatial learning only requires a minislab of dorsal hippocampal tissue.