SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2103.03987 · 2021

Selective Replay Enhances Learning in Online Continual Analogical Reasoning

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

In continual learning, a system learns from non-stationary data streams or batches without catastrophic forgetting. While this problem has been heavily studied in supervised image classification and reinforcement learning, continual learning in neural networks designed for abstract reasoning has not yet been studied. Here, we study continual learning of analogical reasoning. Analogical reasoning tests such as Raven's Progressive Matrices (RPMs) are commonly used to measure non-verbal abstract reasoning in humans, and recently offline neural networks for the RPM problem have been proposed. In this paper, we establish experimental baselines, protocols, and forward and backward transfer metrics to evaluate continual learners on RPMs. We employ experience replay to mitigate catastrophic forgetting. Prior work using replay for image classification tasks has found that selectively choosing the samples to replay offers little, if any, benefit over random selection. In contrast, we find that selective replay can significantly outperform random selection for the RPM task.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2103.03987")
get_code_for_paper("2103.03987")
have("2103.03987")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2103.03987.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2103.03987.svg)](https://syntology.ai/paper/2103.03987)

Connect an agent — have() is free.