Skip to content
Back to skills

Continuous Learning In Singleincrementaltask Scenarios

ASecurity

**arXiv ID:** 1806.08568 **Authors:** Davide Maltoni, Vincenzo Lomonaco **Published:** 2018-06-22T09:22:42Z **Abstract:** It was recently shown that architectural, regularization and rehearsal strategies can be used to train deep models sequentially on a number of disjoint tasks without forgetting previously acquired knowledge. However, these strategies are still unsatisfactory if the tasks are not disjoint but constitute a single incremental task (e.g., class-incremental learning). In this p...

  • 3 stars
  • 0 votes
  • 0 copies
  • 0 views
  • Added September 11, 2026
toolsgo

Security analysis

A100/100

Scanned September 11, 2026

npx -y skills add hiyenwong/ai_collection --skill continuous-learning-in-singleincrementaltask-scenarios --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Continuous Learning In Singleincrementaltask Scenarios?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Continuous Learning In Singleincrementaltask Scenarios
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/hiyenwong-continuous-learning-in-singleincrementaltask-scena/badge)](https://www.skillsdirectory.com/skills/hiyenwong-continuous-learning-in-singleincrementaltask-scena)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
# Continuous Learning in Single-Incremental-Task Scenarios

**arXiv ID:** 1806.08568
**Authors:** Davide Maltoni, Vincenzo Lomonaco
**Published:** 2018-06-22T09:22:42Z
**Abstract:**
It was recently shown that architectural, regularization and rehearsal strategies can be used to train deep models sequentially on a number of disjoint tasks without forgetting previously acquired knowledge. However, these strategies are still unsatisfactory if the tasks are not disjoint but constitute a single incremental task (e.g., class-incremental learning). In this paper we point out the differences between multi-task and single-incremental-task scenarios and show that well-known approaches such as LWF, EWC and SI are not ideal for incremental task scenarios. A new approach, denoted as AR1, combining architectural and regularization strategies is then specifically proposed. AR1 overhead (in term of memory and computation) is very small thus making it suitable for online learning. When tested on CORe50 and iCIFAR-100, AR1 outperformed existing regularization strategies by a good margin.

## Skill Description

This skill is generated from the arXiv paper: Continuous Learning in Single-Incremental-Task Scenarios (1806.08568).

## How to Use

[To be filled in by the user or by future automation]

## References

- [arXiv:1806.08568](http://arxiv.org/abs/1806.08568v3)

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

View all in tools →

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.