Jürgen Schmidhuber

@jurgen-schmidhuber · 2 positions · On ppll ↗

Jürgen Schmidhuber did not write this page.

We collected these quotes from things they published elsewhere, and every quote links to where it was said. They have no account here and have not endorsed this site. Quotes are word for word; the short line under each one is our own restatement, not their wording. Their own site. Is this you? Claim it or ask us to remove it. Or tell us what is wrong here.

Filter All topics · Newest first

Topic

All 2 neural networks 2

Sort

Newest Oldest

1 Nov 1997

Our reading
Recurrent backpropagation learns slowly over long intervals mainly because error backflow decays.

neural networks

Their wordsLearning to store information over extended time intervals by recurrent backpropagation takes a very long time, mostly because of insufficient, decaying error backflow.

↗Long Short-Term Memorydoi.org All 4 from this paper
1 Nov 1997

Our reading
LSTM can solve complex artificial long-time-lag tasks that prior recurrent network algorithms never solved.

neural networks

Their wordsLSTM also solves complex, artificial long-time-lag tasks that have never been solved by previous recurrent network algorithms.

↗Long Short-Term Memorydoi.org All 4 from this paper