How Do Computers Learn?
Machine learning is a process through which computerized systems use human-supplied data and feedback to independently make decisions and predictions, typically becoming more accurate with continual training. This contrasts with traditional computing, in which every action taken by a computer must be pre-programmed.
Machine learning powers many features of modern life, including search engines, social media, and self-driving cars, and it is increasingly applied to other areas, such as science and art.
Since machine learning systems use data to make decisions or predictions, biased or incomplete datasets can lead to suboptimal or unintended outcomes.
Computer scientists choose different machine learning approaches depending how the system will be used. For example, reinforcement learning teaches a system as it interacts with an environment by offering it rewards when it performs an action correctly. Two other common approaches that use data are supervised learning, which applies to the computer-vision systems used in autonomous vehicles, and unsupervised learning, which is used when data need to be clustered (for example, audience segmentation for streaming services or product recommendations to online shoppers).
This comic illustrates supervised and unsupervised approaches to machine learning.
Dive Deeper
How AI turns text into images
AI for #MeToo: Training Algorithms to Spot Online Trolls
