• home
• current students
• graduate
• events

Presenter: Samaneh Javadinia
Supervisor:

Date: Tue, September 5, 2023
Time: 13:00:00 - 00:00:00
Place: ZOOM - Please see below.

ABSTRACT

Join Zoom Meeting
https://us05web.zoom.us/j/88956293055?pwd=8tclisH6vUvazdPFmwxOYQeYQyWhFv.1

Meeting ID: 889 5629 3055
Passcode: 5N72PF 

Abstract: Convolutional Neural Networks (CNNs) have produced state-of-the-art results for image classification tasks. However, they are limited in their ability to handle rotational and viewpoint variations due to information loss in max-pooling layers. Capsule Networks (CapsNets) employ a computationally expensive iterative process referred to as dynamic routing to address these issues. CapsNets, however, often fall short on complex datasets and require more computational resources than CNNs. To overcome these challenges, we introduce the Parallel Dynamic Routing CapsNet (PDR-CapsNet), a deeper and more energy-efficient alternative to CapsNet that offers superior performance, less energy consumption, and lower overfitting rates. By leveraging a parallelization strategy, PDR-CapsNet mitigates the computational complexity of CapsNet and increases throughput, efficiently using hardware resources. As a result, we achieve 83.55% accuracy while requiring 87.26% fewer parameters, 32.27% and 47.40% fewer MACs, and Flops, achieving 3x faster inference and 7.29J less energy consumption on a 2080Ti GPU with 11GB VRAM compared to CapsNet and for the CIFAR-10 dataset.