SECAI Core · phase 1 of 15 · noun
Deep learning
A refinement of machine learning that enables a machine to develop strategies for solving a task given a labeled dataset and without further explicit instructions.
The Explain card
- Plain English
- Deep learning is machine learning using many-layered neural networks. Given a labeled dataset, the network works out its own useful features and strategies without explicit instructions.
- Example
- A phishing detector is shown raw screenshots of login pages labeled "real" or "fake". Instead of engineers choosing features, the network learns by itself which visual cues betray a fake.
- Why it matters
- Because the network invents its own features, nobody can fully read its reasoning. That opacity hides bias, backdoors and strange failure modes, and it is what makes adversarial examples possible.
- Hook
- More layers, more power, less visibility into why.
Word knowledge
How the word is built, where it came from, and what it sits beside in memory.
In a sentence
The sandbox runs a deep learning classifier on the raw bytes of each uploaded executable before the sample is detonated.
Why these words
- deep Old English dēop, extending far down supplies the depth half, so the learning hangs on many stacked layers rather than a shallow net
- learning Old English leornung, the act of getting knowledge names the classroom activity the phrase assigns to that stack
Where it came from
- Origin
- English compound from Old English dēop (extending far down) and leornung (the act of getting knowledge); as a neural-net label, popularized by Geoffrey Hinton and colleagues
- Entered the language
- 2006
- What changed
- Deep had meant extending far down, then profound. Learning had meant a person acquiring knowledge. Rina Dechter used the pair in 1986 for a search that looked many steps ahead. Neural-net labs then used the same adjective for stacked hidden layers, and Hinton's 2006 papers made the pair the everyday name for that style of training.
How it is spelled
- Pattern
- ee spells the long /iː/ in native English deep, keep, sleep
- Pattern
- -ing turns a verb into a noun of activity
- Breaks the pattern
- the noun phrase stays two words; the hyphen appears only when it modifies another noun
- Breaks the pattern
- deep keeps ee from Old English ēo, while cheap and leap took ea for the same sound
Spelled like
- keep
- sleep
- steep
- training
Broken into chunks
-
deep
- deepen
- deeply
- deepfake
-
learn
- learner
- unlearn
- relearn
-
ing
- training
- computing
- reasoning
What it sits beside
Same subject
- machine learning
- neural network
- convolutional neural network
- transformer
Same shape
Learning compounds
Deep compounds
- deepfake
- deep web
- deep freeze
Core AI paradigms
Where it sits in the deck
Phase 1: What AI Is: Core Concepts and Paradigms
You cannot secure, govern, or attack something you cannot define — establish what AI actually is before any other concept can land.