Recurrent Neural Networks (RNNs)
1 statements across 1 episodes · 0 bullish · 0 bearish · 1 people on the record · first statement May 1, 2026 by Francois Chaubard · across every show →
Everything said about Recurrent Neural Networks (RNNs), oldest first
May 1, 2026 neutral
Chaubard: Prior to 2016, Researchers Believed RNNs Were Necessary for AGI
“An RNN is just a model that you recursively call again and again and again on itself, and we, We're very much in the belief that this was required to get to AGI peak RNN use was probably until 2016 with Alex Graves NeurIPS keynote, which is just fantastic, and…”