Network Morphism¶
Network Morphism. Neuron splitting is not the only form of function-preserving network morphism. Indeed, for a linear network and in the absence of activation functions, any decomposition of the weight matrix \(\boldsymbol{W} = \boldsymbol{A}\boldsymbol{B}\) into two shape-compatible matrices is a valid function-preserving morphism. Network Morphism [WWRC16] describes a set of formal requirements for a morphism \(\mathcal{T}\) to be function-preserving. For example, rather than splitting individual neurons, for any matrices \(V \in \mathbb{R}^{k/2\times C_{l-2}}\) and \(Z \in \mathbb{R}^{C_l \times k/2}\), the addition of new neurons with a minus sign inserted
ensures that the contributions of the new weights cancel, preserving the network function.
References¶
Tao Wei, Changhu Wang, Yong Rui, and Chang Wen Chen. Network Morphism. In ICML. March 2016. arXiv:1603.01670. URL: http://arxiv.org/abs/1603.01670, doi:10.48550/arXiv.1603.01670.