Machine Learning Overview

What is Machine Learning?

Below are the definition of Machine Learning we googled.

• [Wikipedia] Machine learning is a field of artificial intelligence that uses statistical techniques to give computer systems the ability to "learn" (e.g., progressively improve performance on a specific task) from data, without being explicitly programmed.
• [Nvidia] Machine Learning at its most basic is the practice of using algorithms to parse data, learn from it, and then make a determination or prediction about something in the world.
• [Stanford] Machine learning is the science of getting computers to act without being explicitly programmed.
• [McKinsey & Co.] Machine learning is based on algorithms that can learn from data without relying on rules-based programming.
• [University of Washington] Machine learning algorithms can figure out how to perform important tasks by generalizing from examples.
• [Carnegie Mellon University] The field of Machine Learning seeks to answer the question “How can we build computer systems that automatically improve with experience, and what are the fundamental laws that govern all learning processes?
• [Investopedia] Machine learning is the concept that a computer program can learn and adapt to new data without human interference. Machine learning is a field of artificial intelligence (AI) that keeps a computer’s built-in algorithms current regardless of changes in the worldwide economy.
• [SearchEnterpriseAI] Machine learning (ML) is a category of algorithm that allows software applications to become more accurate in predicting outcomes without being explicitly programmed. The basic premise of machine learning is to build algorithms that can receive input data and use statistical analysis to predict an output while updating outputs as new data becomes available.

From above, we can conclude that the Machine Learning 

• is a field of artificial intelligence
• use algorithms to learn from data
• can predict from new data without relying on rules-based programming

Machine Learning Algorithms

Main categories:

• Supervised Learning - learn from labeled data so as to predict with new data
• Unsupervised Learning - learn from data that has not been labeled, classified or categorized
• Semi-supervised Learning - learn from combination of small amount labeled and massive unlabeled data
• Reinforcement Learning - how software agents ought to take actions in an environment so as to maximize some notion of cumulative reward, e.g. Google’s DeepMind AlphaGo computer

Misc Concepts

Transfer Learning - the technique of applying the trained model to a different but related problem