Machine Learning (AI)

Markov Decision Process
Markov Decision Process. Example of a simple MDP with three states (green circles) and two actions (orange circles), with two rewards (orange arrows).

Machine Learning  as a way to achieve AI is one of  the current hot topic’s in the tech world. AI and machine learning algorithms aren’t new.  The field of AI dates back to the 1950s. An IBM researcher, Arthur Lee Samuels,  developed one of the earliest machine learning programs. He developed a self-learning program for playing checkers. He coined the term machine learning, and his approach to machine learning was explained in a paper published in the IBM Journal of Research and Development in 1959. [source IBM]. A copy can be found here https://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=5392560.  Some of the methods used in ML are supervised learning which uses classification and regression techniques to develop predictive models, unsupervised learning which uses clustering and reinforcement learning which uses Markov decision process (MDP).
Computers use mathematical algorithms to learn, and different algorithms learn in different ways and are used for different solutions using ML.