AI Paper Atlas

Research map / Continual learning / Online and replay-based

Generative Continual Concept Learning

Mohammad Rostami, Soheil Kolouri, Praveen Pilly, James McClelland

AAAI 2020 · Continual learning › Online and replay-based · approach: Unified and unsupervised continual frameworks · 38 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
Use ECLA with generative replay instead of classic backpropagationSequential permuted MNIST · Permuted MNISTperformance on previously learned tasksImproved
Use full experience replay with stored past-task data instead of ECLASequential permuted MNIST · Permuted MNISTperformance on previously learned tasksImproved
Use ECLA rather than full experience replaySequential permuted MNIST · Permuted MNISTcross-domain concept alignmentImproved
Learn a second digit-recognition domain with ECLA and 10 labeled examples per classECLA · MNIST → USPS and USPS → MNISTperformance on the first task after learning the secondImproved
Transfer from the first digit-recognition domain using ECLAECLA · MNIST → USPS and USPS → MNISTinitial performance on the second taskImproved
Use ECLA on visually similar domains rather than unrelated domainsECLA · Digit recognition versus permuted MNISTtask-agnostic concept formationMixed

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