Jump to content

deep learning

From Wiktionary, the free dictionary
See also: Deep Learning

English

[edit]

Etymology

[edit]

Coined by Israeli-American computer scientist Rina Dechter in 1986, in the context of backtracking in theorem proving. Later applied to multilayered (“deep”) neural networks by Geoffrey Hinton.

Noun

[edit]

deep learning (uncountable)

  1. (machine learning) A form of machine learning based on the interpretation of the structure of data.
    Synonym: DL (initialism)
    Hypernyms: ML, machine learning < learning
    Hyponyms: RL, reinforcement learning
    • 1986 August 11, Rina Dechter, “Learning while searching in constraint-satisfaction-problems”, in Proceedings of the Fifth AAAI National Conference on Artificial Intelligence (AAAI'86), Philadelphia, Pennsylvania: AAAI Press, →DOI, pages 178–183:
      Discovering all minimal conflict-sets amounts to acquiring all the possible information out of a dead-end. Yet, such deep learning may require considerable amount of work.
    • 2012 November 23, John Markoff, “Scientists See Promise in Deep-Learning Programs”, in New York Times[1]:
      Deep learning was given a particularly audacious display at a conference last month in Tianjin, China, when Richard F. Rashid, Microsoft’s top scientist, gave a lecture in a cavernous auditorium while a computer program recognized his words and simultaneously displayed them in English on a large screen above his head.

Derived terms

[edit]
[edit]

Translations

[edit]

Further reading

[edit]

Italian

[edit]

Etymology

[edit]

Unadapted borrowing from English deep learning.

Noun

[edit]

deep learning m (invariable)

  1. (computing, neologism) deep learning