Sparsity-Probe: Analysis tool for Deep Learning Models

05/14/2021
by   Ido Ben-Shaul, et al.
27

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.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset