Machine learning algorithms are programs (math and logic) that adjust themselves to perform better as they are exposed to more data. 

 Deep learning algorithms can be applied to unsupervised learning tasks. This is an important benefit because unlabeled data are more abundant than the labeled data.

Chapter 1 : Supervised learning

In general, supervised learning occurs when a system is given input and output variables with the intentions of learning how they are mapped together, or related. 

The most widely used learning algorithms are
  • Linear regression
  • Logistic regression etc

Chapter 2 : Unsupervised learning

Unsupervised learning algorithms allows you to perform more complex processing tasks compared to supervised learning. 

The most common algorithms used in unsupervised learning include K-means clustering algorithm.

Chapter 3 : Neural network

The artificial neural network can perform the tasks that the linear programs cannot perform. 

Here are the most important types of neural networks are

  • Convolutional Neural Network (CNN)
  • Recurrent Neural Network (RNN)