Back to timeline

Research · 1990

Finding Structure in Time

Elman gave a network a context layer holding its own previous state, and showed that it then learns the structure of a sequence.

Why it matters

Time stopped being an extra input and became internal state, the form recurrent networks still work in.

The network predicted the next word in a sentence. Analysis of the hidden layer showed it had grouped words into nouns, verbs, and animate against inanimate by itself, though nobody had supplied categories or labels. Elman also showed the limit: the further the dependency, the weaker the signal, which is what Hochreiter explained formally the next year.

Event record

Event date
1990
Timeline date
Event date
Verification
Sources gathered automatically · September 17, 2026
Lines
ID
evt-0162

Cognitive Science volume 14, issue 2, 1990.

Sources

Related events

Records that link to this one