Computational complexity reduction of deep neural networks
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.
Fields of Study & Subjects
Advanced Neural Network Applications
Neural Networks and Applications
Parallel Computing and Optimization Techniques
Publication details
- Journal / source
- Contemporary mathematics - American Mathematical Society
- Pages
- 73–88
- Publication date
- 1 January 2026
- Language
- EN