Vamshi Madala

Vamshi Madala

PhD, Electrical and Computer Engineering, UCSB

Publications

CNNs Avoid the Curse of Dimensionality by Learning on Patches

Published in IEEE Open Journal of Signal Processing, vol. 4, pp. 233-241, 2023, 2023

We propose a theory for generalization performance of CNNs on image classification under the hypothesis that CNNs operate on the domain of image patches. Ours is the first work we are aware of to derive an a priori error bound for the generalization error of CNNs and we present both quantitative and qualitative evidences in the support of our theory.

Recommended citation: V. C. Madala, S. Chandrasekaran and J. Bunk, "CNNs Avoid the Curse of Dimensionality by Learning on Patches," in IEEE Open Journal of Signal Processing, vol. 4, pp. 233-241, 2023, doi: 10.1109/OJSP.2023.3270082. https://ieeexplore.ieee.org/abstract/document/10107763

Thesis: A Study of Generalization in Deep Neural Networks

Published in University of California, Santa Barbara, 2021

Understanding generalization of DNNs by investigating the role of different attributes of DNNs, both structural - such as width, depth, kernel parameters, skip connections, etc - as well as functional - such as intermediate feature representations, receptive fields of CNN kernels

Recommended citation: Vamshi C Madala. 2021. A study of generalization in deep neural networks. University of California, Santa Barbara. https://www.proquest.com/docview/2604320736/abstract/967E2748BD3A4BFAPQ/1?accountid=14522

Understanding and Visualizing Generalization in UNets

Published in Medical Imaging with Deep Learning (MIDL) 2021 in Lübeck, Germany, 2021

We propose techniques for understanding and visualizing the generalization performance of UNets in image classification and regression tasks, as well as metrics that are indicative of performance on unseen, unlabeled data.

Recommended citation: Rajagopal, A., Madala, V.C., Hope, T.A.; Larson, P.. (2021). Understanding and Visualizing Generalization in UNets. *Proceedings of the Fourth Conference on Medical Imaging with Deep Learning*, in *Proceedings of Machine Learning Research* 143:665-681 Available from https://proceedings.mlr.press/v143/rajagopal21a.html. https://2021.midl.io/proceedings/rajagopal21.pdf