Skip to content
Back to skills

Overcoming Catastrophic Forgetting With Hard Attention To The Task

ASecurity

**arXiv ID:** 1801.01423 **Authors:** Joan Serrà, Dídac Surís, Marius Miron, Alexandros Karatzoglou **Published:** 2018-01-04T16:22:22Z **Abstract:** Catastrophic forgetting occurs when a neural network loses the information learned in a previous task after training on subsequent tasks. This problem remains a hurdle for artificial intelligence systems with sequential learning capabilities. In this paper, we propose a task-based hard attention mechanism that preserves previous tasks' informati...

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

Security analysis

A100/100

Scanned September 11, 2026

npx -y skills add hiyenwong/ai_collection --skill overcoming-catastrophic-forgetting-with-hard-attention-to-the-task --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Overcoming Catastrophic Forgetting With Hard Attention To The Task?

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

Security grade badge for Overcoming Catastrophic Forgetting With Hard Attention To The Task
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/hiyenwong-overcoming-catastrophic-forgetting-with-hard-atten/badge)](https://www.skillsdirectory.com/skills/hiyenwong-overcoming-catastrophic-forgetting-with-hard-atten)

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
# Overcoming catastrophic forgetting with hard attention to the task

**arXiv ID:** 1801.01423
**Authors:** Joan Serrà, Dídac Surís, Marius Miron, Alexandros Karatzoglou
**Published:** 2018-01-04T16:22:22Z
**Abstract:**
Catastrophic forgetting occurs when a neural network loses the information learned in a previous task after training on subsequent tasks. This problem remains a hurdle for artificial intelligence systems with sequential learning capabilities. In this paper, we propose a task-based hard attention mechanism that preserves previous tasks' information without affecting the current task's learning. A hard attention mask is learned concurrently to every task, through stochastic gradient descent, and previous masks are exploited to condition such learning. We show that the proposed mechanism is effective for reducing catastrophic forgetting, cutting current rates by 45 to 80%. We also show that it is robust to different hyperparameter choices, and that it offers a number of monitoring capabilities. The approach features the possibility to control both the stability and compactness of the learned knowledge, which we believe makes it also attractive for online learning or network compression applications.

## Skill Description

This skill is generated from the arXiv paper: Overcoming catastrophic forgetting with hard attention to the task (1801.01423).

## How to Use

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

## References

- [arXiv:1801.01423](http://arxiv.org/abs/1801.01423v3)

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.