engleski

Data Classification Based on Machine Learning

Machine learning is a part of artificial intelligence aiming to develop computer algorithms which will be able to automate decisions by learning from provided examples. Support vector machines and Random forests are two machine learning approaches widely used in the data classification problem. Data classification attempts to assign a set of observations to their known groups based on general rules extracted from the characteristics describing the observations. The learned rules are applied afterwards to predict to which group a new observation belongs.

GWAS; glycosylation; SNPs; machine learning

nije evidentirano