Browse Definitions :
Definition

active learning (active learner algorithm)

Active learning, in an AI context, is the capacity of a machine learning (ML) algorithm to query a human source for additional information. Essentially, active learning allows a minimally-trained AI program to identify what data it needs to become better. The algorithm identifies which subset of data it expects to yield the best results for a particular category and requests that someone label the data in that subset. 

Active learning algorithms require minimal training data, which makes them especially helpful when there’s not a lot of labeled data available. This makes this type of algorithm useful for information retrieval and text analysis -- as well as image and speech recognition.

Active learning vs. supervised learning vs. unsupervised learning

Active learning algorithms are a simple form of semi-supervised, curious AI. This type of algorithm combines aspects of both supervised learning and unsupervised learning.

Supervised ML, which uses historic data to make forecasts about new data, requires a human to create input and desired-output data for training. Because this approach requires a lot of human overhead, it can be expensive. In contrast, AI systems that use unsupervised learning require very little human overhead because the algorithms simply look for patterns in unlabeled datasets. While this type of ML can be cost-effective because it does not require as much human input, it can also be difficult to quantify the results as being meaningful. 

Active learning can use both structured and unstructured data in a cost-efficient manner by prioritizing which data the model is most confused about and requesting labels for just that data. The model will use a relatively small amount of labeled data for training and request more labels later on if needed. This iterative approach to machine learning not only helps the machine learning model learn faster, it also keeps costs down by letting humans skip labeling data that isn't helpful to the model.

Watch this introductory tutorial on active learning to learn more.

This was last updated in December 2019

Continue Reading About active learning (active learner algorithm)

SearchCompliance

  • information governance

    Information governance is a holistic approach to managing corporate information by implementing processes, roles, controls and ...

  • enterprise document management (EDM)

    Enterprise document management (EDM) is a strategy for overseeing an organization's paper and electronic documents so they can be...

  • risk assessment

    Risk assessment is the identification of hazards that could negatively impact an organization's ability to conduct business.

SearchSecurity

  • honeypot (computing)

    A honeypot is a network-attached system set up as a decoy to lure cyber attackers and detect, deflect and study hacking attempts ...

  • spam trap

    A spam trap is an email address that is used to identify and monitor spam email.

  • cracker

    A cracker is someone who breaks into someone else's computer system, often on a network; bypasses passwords or licenses in ...

SearchHealthIT

SearchDisasterRecovery

  • risk mitigation

    Risk mitigation is a strategy to prepare for and lessen the effects of threats faced by a business.

  • call tree

    A call tree is a layered hierarchical communication model that is used to notify specific individuals of an event and coordinate ...

  • Disaster Recovery as a Service (DRaaS)

    Disaster recovery as a service (DRaaS) is the replication and hosting of physical or virtual servers by a third party to provide ...

SearchStorage

  • cloud testing

    Cloud testing is the process of using the cloud computing resources of a third-party service provider to test software ...

  • storage virtualization

    Storage virtualization is the pooling of physical storage from multiple storage devices into what appears to be a single storage ...

  • erasure coding

    Erasure coding (EC) is a method of data protection in which data is broken into fragments, expanded and encoded with redundant ...

Close