Applying Occam’s razor to Deep Learning

Finding a deep learning model to perform well is an exciting feat. But, might there be other -- less complex -- models that perform just as well for your application? A simple complexity measure based on the statistical physics concept of Cascading Periodic Spectral Ergodicity (cPSE) can help us be computationally efficient by considering the least complex during model selection.

Check out the full article at KDNuggets.com website
Applying Occam’s razor to Deep Learning