Sparsity-Probe: Analysis tool for Deep Learning Models
From MaRDI portal
Abstract: We propose a probe for the analysis of deep learning architectures that is based on machine learning and approximation theoretical principles. Given a deep learning architecture and a training set, during or after training, the Sparsity Probe allows to analyze the performance of intermediate layers by quantifying the geometrical features of representations of the training set. We show how the Sparsity Probe enables measuring the contribution of adding depth to a given architecture, to detect under-performing layers, etc., all this without any auxiliary test data set.
This page was built for publication: Sparsity-Probe: Analysis tool for Deep Learning Models
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6367655)
