FastNet

TL;DR

FastNet is a new neural network architecture optimized for high computational efficiency, enabling deployment on edge devices while maintaining competitive accuracy on standard datasets.

Contribution

Introduces a novel architecture that balances high accuracy with low computational cost, suitable for edge deployment, outperforming ResNet in efficiency.

Findings

Achieves competitive accuracy on CIFAR 10 and CIFAR 100

Demonstrates high efficiency on GPUs and CPUs

Suitable for deployment on mobile and IoT devices

Abstract

Inception and the Resnet family of Convolutional Neural Network archi-tectures have broken records in the past few years, but recent state of the art models have also incurred very high computational cost in terms of training, inference and model size. Making the deployment of these models on Edge devices, impractical. In light of this, we present a new novel architecture that is designed for high computational efficiency on both GPUs and CPUs, and is highly suited for deployment on Mobile Applications, Smart Cameras, Iot devices and controllers as well as low cost drones. Our architecture boasts competitive accuracies on standard Datasets even out-performing the original Resnet. We present below the motivation for this research, the architecture of the network, single test accuracies on CIFAR 10 and CIFAR 100 , a detailed comparison with other well-known architectures and link to an implementation in Keras.