A popular type of machine learning algorithm is called a neural network. The neural network is formed to represent the human brain structure and its functions with interconnected layers of nodes that work together to break down complex data. This form of algorithm is well suited for identifying complex patterns and relationships within large amounts of data.


The simplest form of machine learning is called supervised learning which uses labeled data sets to train algorithms to classify data and predict outcomes. Humans pair the training examples with outputs and through this the model can learn the mapping of inputs and outputs within the training data. In thus allowing the model to predict the labels of unseen data.


Through the usage of deep learning which is a subset of machine learning that uses multilayered neural networks to simulate the complex decision making of the human brain. These layers enable unsupervised learning which allows the machine to automate the extraction of features from large unlabeled and unstructured data sets allowing it to make its own predictions on what the data represents.