AI Paper Atlas

Research map / Continual learning / Online and replay-based

Organizing recurrent network dynamics by task-computation to enable continual learning

Lea Duncker, Laura Driscoll, Krishna V. Shenoy, Maneesh Sahani, David Sussillo

NeurIPS 2020 · Continual learning › Online and replay-based · approach: Theoretical analysis of forgetting · 51 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 plain SGD with projected-update continual learning rule in sequential trainingRNN on DelayPro/DelayAnti/MemoryPro/MemoryAnti · Sequential multi-task neuroscience taskstask performance after sequenceImproved
use projected-update rule instead of EWCsequentially trained RNN · Sequential multi-task neuroscience taskstask performance after sequenceImproved
use projected-update rule instead of synaptic intelligencesequentially trained RNN · Sequential multi-task neuroscience taskstask performance after sequenceImproved
pretrain on a task with the same stimulus-response relationship before second task (ablation)sequentially trained RNN · Second-task learning speedtest log cost decrease rateImproved
train simultaneously on all tasks instead of sequentially with the ruleRNN · Four multi-task suitetask performanceImproved
project out subspace of same-relationship task vs opposite-relationship task (ablation)trained RNN · Hidden-state perturbationtask performanceHurt

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