# LG AI Research — SISE (Semantic Input Sampling for Explanation) - a novel visual explainable AI

- Company: LG AI Research (lgresearch.ai)
- Announced: 2021-02-09
- Category: research-paper
- Coverage: not counted
- Announcement: yes
- Group: announcements
- Source: https://www.lgresearch.ai/blog/view?seq=67
- Record: https://forck.live/items/5001-sise-semantic-input-sampling-for-explanation-a-novel-visual-explainable-ai
- Subject: EXAONE

LG AI Research introduces SISE (Semantic Input Sampling for Explanation), a novel visual explainable AI method that improves faithfulness and reduces computation time compared to existing XAI methods. The method is described in their AAAI-21 paper.

## Evidence

Verbatim from https://www.lgresearch.ai/blog/view?seq=67:

> LG AI Research has developed a novel XAI algorithm, called "Semantic Input Sampling for Explanation (SISE)" in collaboration with Prof. Konstantinos Plataniotis at the University of Toronto. It achieves higher faithfulness and correctness than the previously mentioned XAI methods. Additionally, it takes less computation time.

---

Record: https://forck.live/items/5001-sise-semantic-input-sampling-for-explanation-a-novel-visual-explainable-ai
Catalogue: https://forck.live/llms.txt
Current issue: https://forck.live/feed.md