Deep Neural Networks via Complex Network Theory: a Perspective

arXiv:2404.11172v2 Announce Type: replace
Abstract: Deep Neural Networks (DNNs) can be represented as graphs whose links and vertices iteratively process data and solve tasks sub-optimally. Complex Network Theory (CNT), merging statistical physics with graph theory, provides a method for interpreting neural networks by analysing their weights and neuron structures. However, classic works adapt CNT metrics that only permit a topological analysis as they do not account for the effect of the input data. In addition, CNT metrics have been applied …

abstract arxiv cs.ai cs.lg data graph graphs however merging network networks neural networks neuron perspective physics process solve statistical tasks theory type via