Browse Definitions :
Definition

target function

Contributor(s): Matthew Haughn

A target function, in machine learning, is a method for solving a problem that an AI algorithm parses its training data to find. Once an algorithm finds its target function, that function can be used to predict results (predictive analysis). The function can then be used to find output data related to inputs for real problems where, unlike training sets, outputs are not included.

The target function is essentially the formula that an algorithm feeds data to in order to calculate predictions. As in algebra, it is common when training AI to find the variable from the solution, working in reverse. The function as defined by f is applied to the input (I) to produce the output (I), Therefore O= f(I).

Analyzing the massive amounts of data related to its given problem, an AI derives understanding of previously unspecified rules by detecting consistencies in the data. The observations of inherent rules about how the studied subject operates inform the AI on how to process future data that does not include an output by applying this previously unknown function.

This was last updated in June 2018

Continue Reading About target function

Start the conversation

Send me notifications when other members comment.

Please create a username to comment.

-ADS BY GOOGLE

File Extensions and File Formats

Powered by:

SearchCompliance

  • PCI DSS (Payment Card Industry Data Security Standard)

    The Payment Card Industry Data Security Standard (PCI DSS) is a widely accepted set of policies and procedures intended to ...

  • risk management

    Risk management is the process of identifying, assessing and controlling threats to an organization's capital and earnings.

  • compliance framework

    A compliance framework is a structured set of guidelines that details an organization's processes for maintaining accordance with...

SearchSecurity

  • DNS over HTTPS (DoH)

    DNS over HTTPS (DoH) is a relatively new protocol that encrypts domain name system traffic by passing DNS queries through a ...

  • integrated risk management (IRM)

    Integrated risk management (IRM) is an approach to risk management that uses a set of practices and processes to improve an ...

  • MITRE ATT&CK framework

    The MITRE ATT&CK (pronounced 'miter attack') framework is a free, globally accessible service that provides comprehensive and ...

SearchHealthIT

  • telemedicine (telehealth)

    Telemedicine is the remote delivery of healthcare services, such as health assessments or consultations, over the ...

  • Project Nightingale

    Project Nightingale is a controversial partnership between Google and Ascension, the second largest health system in the United ...

  • medical practice management (MPM) software

    Medical practice management (MPM) software is a collection of computerized services used by healthcare professionals and ...

SearchDisasterRecovery

SearchStorage

  • M.2 SSD

    An M.2 SSD is a solid-state drive (SSD) that conforms to a computer industry specification and is used in internally mounted ...

  • kilobyte (KB or Kbyte)

    A kilobyte (KB or Kbyte) is a unit of measurement for computer memory or data storage used by mathematics and computer science ...

  • virtual memory

    Virtual memory is a memory management capability of an operating system (OS) that uses hardware and software to allow a computer ...

Close