Computational complexity reduction of deep neural networks
This addresses the challenge of deploying DNNs on edge devices with low computational resources, but it appears incremental as it focuses on optimization rather than a breakthrough.
The paper tackles the problem of deep neural networks being computationally complex for deployment on resource-constrained platforms, proposing methods to reduce complexity and accelerate training and inference speeds for edge computing.
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.