Hosted on MSN

KAIST team develops brain-inspired method to curb AI overconfidence

Researchers at KAIST have introduced a brain-inspired training method that reduces AI overconfidence by briefly exposing ...
Tech Xplore

How everyday devices could train AI faster while keeping personal data on-device

A new method developed by MIT researchers can accelerate a privacy-preserving artificial intelligence training method by ...
Frontiers

Synergic entanglements between Structural Biology and Machine Learning: Looking into the future

The rapid advances in machine learning (ML) and artificial intelligence (AI) are transforming biology and opening new directions for scientific inquiry.
Assembly Magazine

Machine Learning Detects Fastening Errors

Ford engineers are studying whether AI can play a role in detecting faulty run-downs. To do that, they first had to determine ...
The Lancet

From prediction to navigation for artificial intelligence in medicine

Whether estimating the probability that a disease is present or forecasting risk of deterioration,1 readmission,2 or death,3 most contemporary clinical artificial intelligence (AI) systems are ...
IEEE

Invisible Backdoor Attack against Self-supervised Learning

Abstract: Self-supervised learning (SSL) models are vulnerable to backdoor attacks. Existing backdoor attacks that are effective in SSL often involve noticeable triggers, like colored patches or ...
IEEE

Confidence-Aware Superpixel Self-Supervised Learning for Cross-Modal Point Cloud Recognition

Abstract: The high cost of 3-D annotation severely limits the availability of high-quality labeled data, posing a critical bottleneck to point cloud recognition tasks. In contrast, acquiring and ...