Research published in Elsevier’s Pattern Recognition Journal

Nidhi Gowdra’s research article, titled “Mitigating severe over-parameterization in deep convolutional neural networks through forced feature abstraction and compression with an entropy-based heuristic” co-authored with Roopak Sinha, Stephen MacDonell and Wei Qi Yan, has been accepted at Elsevier’s Pattern Recognition Journal (h-index 210).