Machine Learning

Here you’ll find all articles that use machine learning, whether it’s classic machine learning such as random forests or logistic regression, or deep learning.

Machine learning is a generic term for the “artificial” generation of knowledge from experience. This means that an artificial system learns from examples by recognizing patterns and regularities. For this purpose, algorithms build a statistical model based on training data. Such a system can also assess unknown data and make own assumptions. There are two groups of machine learning algorithms: supervised learning and unsupervised learning. In supervised learning, the training process is based on prelabeled data. This means that the algorithm can compare its predictions to the correct answers. In this way, the algorithm learns from errors by adjusting the statistical model. In contrast, in unsupervised learning, the training data is unlabeled. Therefore, the algorithm does not know if its predictions are right or wrong and thus needs to come to own conclusions.