<ul><li>A new research work presents a theory on when biologically inspired networks modularize their representation of source variables.</li><li>The theory provides necessary and sufficient conditions for modularization based on the spread of support of the sources.</li><li>The research validates the theory by applying it to various empirical studies on nonlinear neural networks.</li><li>The results suggest alternate origins of mixed-selectivity, contributing to a better understanding of modular representations.</li></ul>

Range, not Independence, Drives Modularity in Biologically Inspired Representations

Discover more