Back to timeline

Research · March 1994

Why long-term dependencies are not learned

Bengio, Simard and Frasconi proved that gradient training of recurrent networks cannot both hold information for a long time and stay robust to noise.

Why it matters

The problem was stated as a trade-off rather than an implementation flaw: only a change of architecture gets around it.

The authors show that the condition for stably storing state contradicts the condition under which the gradient does not vanish. Tuning the learning rate or the initialisation therefore cannot fix it. The paper appeared in English in a refereed journal and so influenced the field more than Hochreiter's German-language thesis, though it came three years later.

Event record

Event date
March 1994
Timeline date
Event date
Verification
Sources gathered automatically · September 17, 2026
Lines
ID
evt-0170

IEEE Transactions on Neural Networks volume 5, issue 2, March 1994.

Sources

Related events