Multi-Scale Structural Features for Continual, Comprehensible Visual Recognition in a Developmental Learning Framework

תקציר מקורי באנגליתarXiv:2607.25531v1 Announce Type: cross Abstract: Contemporary machine learning struggles to learn continually, reuse prior knowledge, and expose a comprehensible internal structure. A recently proposed developmental, gradient-free learning framework addresses these limitations by learning a discrete, topological model of its inputs through local variation and selection, yielding an inherent continual-learning guarantee: new observations refine existing structure without overwriting past knowledge, and without replay buffers or predefined task boundaries. Its extension to visual inputs demonstrated this principle on shape recognition, but relied on a feature representation of limited expressivity that capped recognition accuracy. We introduce a new visual feature representation that encode