Selectivity metrics provide misleading estimates of the selectivity of single units in neural networks

AbstractTo understand the representations learned by neural networks (NNs), various methods of measuring unit selectivity have been developed. Here we undertake a comparison of four such measures on AlexNet: localist selectivity; precision; class-conditional mean activity selectivity CCMAS; and top-class selectivity. In contrast with previous work on recurrent neural networks (RNNs), we fail to find any 100\% selective `localist units' in AlexNet, and demonstrate that the precision and CCMAS measures are misleading and suggest a much higher level of selectivity than is warranted. We also generated activation maximization (AM) images that maximally activated individual units and found that under (5%) of units in fc6 and conv5 produced interpretable images of objects, whereas fc8 produced over 50% interpretable images. Furthermore, the interpretable images in the hidden layers were not associated with highly selective units. We also consider why localist representations are learned in RNNs and not AlexNet.


Return to previous page