other · Contemporary mathematics - American Mathematical Society · 2026
Computational complexity reduction of deep neural networks
Cited by 0Abstract and details only
Abstract
Deep neural networks (DNN) have been widely used and play a major role in the field of computer vision and autonomous navigation. However, these DNNs are computationally complex and their deployment over resource-constrained platforms is difficult without additional optimizations and customization. In this manuscript, we provide an overview of DNN architectures and propose methods to reduce computational complexity, thereby accelerating training and inference speed for deployment on edge computing platforms with limited resources.
Cite this paper
Im, M. S., & Dasari, V. (2026). Computational complexity reduction of deep neural networks. Contemporary mathematics - American Mathematical Society, 73–88. https://doi.org/10.1090/conm/835/16753
Im, Mee Seong, and Venkat Dasari. “Computational complexity reduction of deep neural networks.” Contemporary mathematics - American Mathematical Society, 2026, pp. 73–88, https://doi.org/10.1090/conm/835/16753.
Im, Mee Seong, and Venkat Dasari. 2026. “Computational complexity reduction of deep neural networks.” Contemporary mathematics - American Mathematical Society: 73–88. https://doi.org/10.1090/conm/835/16753.
Im, M.S. and Dasari, V. (2026) ‘Computational complexity reduction of deep neural networks’, Contemporary mathematics - American Mathematical Society, pp. 73–88. Available at: https://doi.org/10.1090/conm/835/16753.
@misc{im2026computational,
title = {{Computational complexity reduction of deep neural networks}},
author = {Im, Mee Seong and Dasari, Venkat},
journal = {Contemporary mathematics - American Mathematical Society},
pages = {73--88},
year = {2026},
doi = {10.1090/conm/835/16753}
}Made from the index record. Check names, capitalisation and page numbers against the paper. Need another style? AI for Research has over 10,000.