Unsupervised Cognition
Researchers have introduced a novel unsupervised learning approach for decision-making, inspired by a new framework for cognition. This method constructs a hierarchical representation of input data in an input-agnostic manner. The approach has demonstrated superior performance compared to state-of-the-art unsupervised and even supervised learning methods in various classification tasks, including cancer type classification, while exhibiting more cognition-like behaviors. AI
IMPACT Introduces a novel cognitive-inspired unsupervised learning method that could advance AI decision-making capabilities.