How Do Machines Learn?

Infographic

How Do Machines Learn?

Algorithms are the key to machine learning

You鈥檝e heard of machine learning and seen what it can do, but how exactly do machines learn? The short answer: Algorithms.聽We feed algorithms, which are sets of rules used to help computers perform problem-solving operations, large volumes of data from which to learn. Generally, the more data a machine learning algorithm is provided the more accurate it becomes.

Machine learning algorithms are split into two main categories based on how they interact with data: Supervised and unsupervised. Due to their differences when analyzing data, these two machine learning categories are better suited for solving different problems. All forms of machine learning rely on the availability of a huge quantity of data to train algorithms. In the infographic below you鈥檒l see how both supervised and unsupervised ingest this data and which problems they are suited for solving.聽

Download Full Infographic

鈥淐hildren don鈥檛 have adults telling them what each pixel represents in every image they see, or what are the objects present in every image, what is the grammatical structure and the fine sense of every word in every sentence they hear. We extract most of the information from simple observation, and that is what unsupervised learning in principle does.鈥�

- Yoshua Bengio, world-renowned MI expert, January 2016

Sometimes researchers combine these approaches in a method called 鈥渟emi-supervised learning.鈥� In this approach, machine learning algorithms are given a small amount of labeled training data and a much larger pool of unlabeled data from which to learn. This approach can combine the best of both worlds鈥攊mproved accuracy associated with supervised machine learning and the ability to make use of unlabeled data, as in the case of unsupervised machine learning.