{"id":1374,"date":"2019-02-15T10:32:06","date_gmt":"2019-02-15T10:32:06","guid":{"rendered":"http:\/\/kusuaks7\/?p=979"},"modified":"2023-08-08T06:20:00","modified_gmt":"2023-08-08T06:20:00","slug":"coding-deep-learning-for-beginners-types-of-machine-learning","status":"publish","type":"post","link":"https:\/\/www.experfy.com\/blog\/ai-ml\/coding-deep-learning-for-beginners-types-of-machine-learning\/","title":{"rendered":"Coding Deep Learning For Beginners\u200a – \u200aTypes of Machine Learning"},"content":{"rendered":"

Ready to learn Machine Learning? Browse courses<\/a>\u00a0like\u00a0Machine Learning Foundations: Supervised Learning<\/a> developed by industry thought leaders and Experfy in Harvard Innovation Lab.<\/em><\/strong><\/p>\n

This is the 2nd article of series \u201cCoding Deep Learning for Beginners<\/strong>\u201d. You can view the 1st article here<\/a>.\u200b<\/p><\/blockquote>\n

<\/p>\n

Goals<\/strong><\/h3>\n

Getting into Machine Learning isn\u2019t an easy thing. I really want to\u00a0take good care of the reader<\/strong>. That\u2019s why from time to time, you can expect\u00a0articles focused only on theory<\/strong>. Because long articles discourage from learning, I will keep them at\u00a05\u20138 minutes of reading time<\/strong>. I cannot just put everything into a single article \u2014 code snippets, math, terminology \u2014 because that would result in reducing the explanations of essential concepts. I believe that dividing the knowledge into smaller parts and expanding it across more articles will\u00a0make the learning process smooth<\/strong>\u00a0as there will be no need to take stops and detours.<\/p>\n

Machine Learning\u00a0model<\/strong><\/h3>\n

Starting with the definition of \u201cmodel\u201d which will appear quite often from now on. The names like\u00a0Linear Regression<\/em>,\u00a0Logistic Regression<\/em>,\u00a0Decision Trees etc. are just the names of the algorithms. Those are just\u00a0theoretical concepts\u00a0<\/strong>that describe what to do in order to achieve the specific effect. Model is a\u00a0mathematical formula<\/strong>\u00a0which is a result of Machine Learning\u00a0algorithm implementation<\/strong>\u00a0(in case of these articles \u2014 in code). It has measurable parameters that can be used for prediction. Models can be trained by modifying their parameters in order to achieve better results. It is possible to say that models are representations of what a Machine Learning system has learned from the training data.<\/p>\n

<\/canvas><\/figure>\n

Diagram visualising difference between Machine Learning Algorithm and Machine Learning\u00a0Model.<\/p>\n

Branches of Machine\u00a0Learning<\/strong><\/h3>\n

There are three most regularly listed categories of Machine Learning:<\/p>\n