1
Why machine learning struggles with causality
Machine learning systems thrive on finding and exploiting statistical regularities. This is why they can't do causal reasoning.
Ben Dickson
- Popular posts
- 4
- Total points
- 593
- HN comments
- 687
- Rank
- #4,226 personal
Visit bdtechtalks.com → RSS feedOn Hacker News Sep 2020 – Oct 2023
AI & Machine Learning 4Math & Algorithms 2Security & Privacy 1Software Engineering 1
2
LLMs can't self-correct in reasoning tasks, DeepMind study finds
A study by Google's DeepMind and the University of Illinois at Urbana-Champaign has found that self-correction in large language models (LLMs) isn't universally effective.
3
Why neural networks struggle with the Game of Life
The Game of Life is based on very simple rules, but artificial neural networks struggle to learn its rules through the classic deep learning training process.
4
If AI can read, then plain text can be weaponized (2019)
Advances in AI have helped automate many tasks that involve processing text. However, text-processing AI algorithms have their own unique vulnerabilities, researchers at IBM, Amazon and University of Texas have found.