AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

Online learning of long-range dependencies

Nicolas Zucchet, Robert Meier, Simon Schug, Asier Mujika, Joao Sacramento

NeurIPS 2023 · Architectures and efficiency › RNNs and normalization · approach: LSTM design and memory · 4 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
replace LRU with dense linear RNN layer (SnAp-1 online) (ablation)online learning rule · Copy task, 4 layersfinal training loss: 8.44 \times 10^{-3} -> 5.82 \times 10^{-1}Hurt
replace LRU with dense linear RNN layer (ablation)online learning rule · LRA sCIFARtest accuracy: 79.59 -> 63.71Hurt
online learning rule vs spatial backproponline learning rule · LRA sCIFARtest accuracy: 58.20 -> 79.59Improved
online learning rule vs 1-step truncated BPTTonline learning rule · LRA IMDBtest accuracy: 84.04 -> 86.48Improved
online learning rule vs spatial backproponline learning rule · LRA ListOpstest accuracy: 32.02 -> 37.62Improved
online rule vs spatial backproponline learning rule · Copy task, LRU 4 layersfinal training loss: 4.66 \times 10^{-1} -> 8.44 \times 10^{-3}Improved
increase GRU depth from 1 to 4 with SnAp-1 (ablation)SnAp-1 on GRU · Copy taskfinal training loss: 3.16 \times 10^{-1} -> 3.27 \times 10^{-1}No clear effect
increase GRU depth from 1 to 4 with BPTT (ablation)BPTT on GRU · Copy taskfinal training loss: 2.61 \times 10^{-1} -> 1.94Improved
SnAp-1 sensitivity approximation vs cruder truncated BPTT on linear RNN (ablation)linear RNN · Copy taskfinal training loss: 5.81 \times 10^{-1} -> 5.82 \times 10^{-1}No clear effect
SnAp-1 extended to multilayer vs spatial backprop on linear RNN (ablation)linear RNN · LRA sCIFARtest accuracy: 50.63 -> 63.71Improved
shift initial eigenvalue |lambda| distribution toward 1 (ablation)online learning rule · Copy taskgradient alignmentNo clear effect
smaller initial |lambda|_min (ablation)online learning rule · Copy tasktraining speedHurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy