deep learning

American  

[deep lur-ning] / ˈdip ˌlɜr nɪŋ /

noun

Computers.

1. an advanced type of machine learning that uses multilayered neural networks to establish nested hierarchical models for data processing and analysis, as in image recognition or natural language processing, with the goal of self-directed information processing.

---

Etymology

Origin of deep learning

First recorded in 1985–90

Example Sentences

While at OpenAI, Karpathy worked on deep learning for generative-AI models and deep reinforcement learning.

From MarketWatch • May 19, 2026

More recently, Tubi combined large language models, or LLMs, with deep learning techniques—enabling it to better understand “the nature of the user’s intent,” Bidgoli says.

From The Wall Street Journal • Apr. 9, 2026

The same mathematics that helps explain why deep learning works also captures what foams have been doing all along.

From Science Daily • Jan. 15, 2026

TPUs specialize in matrix math for deep learning, and in the right circumstances can provide a much better cost structure than Nvidia’s graphics processing units.

From Barron's • Jan. 13, 2026

He was a person of deep learning, versed in the ancient classics, and skilled in several modern languages, a warm friend of liberty, and an early defender of the American cause.

From The Diplomatic Correspondence of the American Revolution, Vol. IX by Sparks, Jared