Multilayer models, machine learning, neural network, computational complexity, computation reduction.
Contributing USMA Research Unit(s)
Army Cyber Institute, Mathematical Sciences, Mathematical Sciences Center
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 describe an overview of DNN architecture and propose methods to reduce computational complexity in order to accelerate training and inference speeds to fit them on edge computing platforms with low computational resources.
Im, Mee Seong and Dasari, Venkat
"Computational complexity reduction of deep neural networks,"
Mathematica Militaris: Vol. 25:
1, Article 1.
Available at: https://digitalcommons.usmalibrary.org/mathematica_militaris/vol25/iss1/1
Analysis Commons, Other Mathematics Commons, Systems Architecture Commons, Theory and Algorithms Commons