Machine learning classifiers are divided into three groups:
Supervised machine-learning
Using labeled datasets to train algorithms that reliably classify data or predict outcomes is called supervised machine learning .
As more data is being introduced into the model, the weights are changed until the model is fitted correctly.
Unsupervised machine-learning
Unsupervised machine learning , analyses, and clusters unlabeled datasets using machine learning methods.
Without the need or help for human interaction, these algorithms uncover hidden patterns or data.
Because of its ability or capabilities to find similarities and differences in data, it’s perfect for exploratory data analysis, cross-selling techniques, consumer segmentation, picture, and pattern recognition .
Semi-supervised machine-learning
Between supervised and unsupervised learning, semi-supervised learning hits a good spot .
It leads to categorization and feature extraction from a more extensive, unlabeled data set using more minor labeled data during training.
Semi-supervised learning can overcome not having enough labeled data to train a supervised learning algorithm.