Skip to content

    Machine Learning

    Machine learning (ML) is the application of computer algorithms that improve automatically through experience. Machine learning algorithms build a model based on sample data, known as “training data,” in order to make predictions or decisions without being explicitly programmed to do so.

    Dilbert on Machine Learning

    Machine learning focuses on the development of computer programs that can access data and use it to learn for themselves. ML algorithms are used in a wide variety of applications, such as email filtering, fraud detection, and computer vision, where conventional algorithms cannot perform as well or dynamically. While machine learning has been around since the 1950s, recent breakthroughs in low-cost cloud storage and processing, easier data collection, and the proliferation of data science frameworks and libraries, have made ML much more widely used.

    Types of Machine Learning

    ML algorithms learn by example, and then apply those self-learning algorithms to uncover insights, determine relationships, and make predictions about future trends. There are several categories of machine learning, largely depending on the nature of the feedback available to the learning system:

    • Supervised learning: The computer is presented with example inputs and their desired outputs, given by a “teacher,” and the goal is to learn a general rule that maps inputs to outputs.
    • Unsupervised learning: No labels are given to the learning algorithm, leaving it on its own to find structure in its input. Unsupervised learning can be a goal in itself (discovering hidden patterns or anomalies in data) or a means towards an end (feature learning).
    • Reinforcement learning: A computer program interacts with a dynamic environment in which it must perform a certain goal (such as driving a vehicle or playing a game against an opponent). As it navigates its problem space, the program is provided feedback, and it works to maximize “rewards” within this setup.
    • Deep learning: Deep learning can use supervised or unsupervised learning. It is differentiated by the algorithmic technique, and uses multiple layers of tensors, or multidimensional data arrays, to progressively extract higher-level features from the raw data. In image processing for example, lower layers may identify visual edges, while higher layers may identify the concepts relevant to a human such as digits or letters or faces.

    Machine learning is considered a discipline within the broader category of artificial intelligence.

    Additional Resources