Semisupervised Learning News Today

Québec Nickel Corp. (“QNI” or the “Company”) is pleased to report the results from an Artificial Intelligence (“AI”) nickel-sulphide-focused targeting exercise at the Company’s Ducros claims which has recently been completed by ALS GoldSpot Discoveries.

Québec Nickel Corp. ; class=js-l-obf link link--blue

The core issue in semi-supervised learning (SSL) lies in how to effectively leverage unlabeled data, whereas most existing methods tend to put a great emphasis on the utilization of high-confidence samples yet seldom fully explore the usage of low-confidence samples. In this article, we aim to utilize low-confidence samples in a novel way with our proposed mutex-based consistency regularization, namely MutexMatch. Specifically, the high-confidence samples are required to exactly predict “what ...