AI Paper Atlas

Research map / Continual learning / Online and replay-based

Natural continual learning: success is a journey, not (just) a destination

Ta-Chu Kao, Kristopher T Jensen, Gido Martijn van de Ven, Alberto Bernacchia, Guillaume Hennequin

NeurIPS 2021 · Continual learning › Online and replay-based · approach: Plasticity-preserving continual reinforcement learning · 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
NCL vs other methods in task-incremental settingNCL · split MNIST and split CIFAR-100average test accuracyImproved
NCL vs other methods in domain-incremental settingNCL · split MNIST and split CIFAR-100average test accuracyImproved
NCL vs OWM in class-incremental settingNCL · split MNIST and split CIFAR-100average test accuracyHurt
NCL vs SI, online EWC and KFAC in class-incremental settingNCL · split MNIST and split CIFAR-100average test accuracyImproved
unit Gaussian prior without hyperparameter optimization (NCL no-prior) (ablation)NCL · split MNIST and split CIFAR-100average test accuracyNo clear effect
NCL vs OWM and DOWMNCL · stimulus-response RNN tasksmean lossImproved
NCL, OWM and DOWM vs KFAC with lambda=1NCL · stimulus-response RNN tasksmean lossImproved
increase KFAC lambda to between 100 and 1000 (ablation)KFAC · stimulus-response RNN tasksmean lossImproved
NCL vs DOWM and KFAC lambda=1 on SMNISTNCL · SMNIST 15 tasksmean classification errorImproved
optimize lambda for KFAC (ablation)KFAC · SMNIST 15 tasksmean classification errorImproved
Laplace-DOWM projection approximation in place of NCL Fisher approximation (ablation)NCL · SMNIST, first taskclassification errorImproved
Laplace-DOWM projection approximation in place of NCL Fisher approximation (ablation)NCL · SMNIST, later tasksclassification errorHurt

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