[PDF][PDF] Architecture with Reduced Parameter Requirements

M Hailesellasie, SR Hasan, F Khalid, F Awwad… - researchgate.net
The success of deep learning has fast paced the evolution of current technology at
unprecedented rate. In particular, deep convolutional meural networks (CNNs) has gained a …

FPGA-based convolutional neural network architecture with reduced parameter requirements

M Hailesellasie, SR Hasan, F Khalid… - … on Circuits and …, 2018 - ieeexplore.ieee.org
The success of deep learning has fast paced the evolution of current technology at
unprecedented rate. In particular, deep convolutional neural networks (CNNs) has gained a …

Efficient implementation of convolutional neural networks on embedded devices

B Yılmaz - 2022 - earsiv.cankaya.edu.tr
In the field of artificial intelligence, deep convolutional neural network models are very
popular because they can yield results close to those of humans. Depending on the …

Efficient Neural Network Architectures

H Cai, S Han - Low-Power Computer Vision, 2022 - taylorfrancis.com
Designing efficient neural network architectures is a widely adopted approach to improve
efficiency, besides compressing an existing deep neural network. A CNN (Convolutional …

Resource-aware optimization of dnns for embedded applications

A Frickenstein, C Unger… - 2019 16th Conference on …, 2019 - ieeexplore.ieee.org
Despite their outstanding success in solving complex computer vision problems, Deep
Neural Networks (DNNs) still require high-performance hardware for real-time inference …

Towards efficient neural network on edge devices via statistical weight pruning

TH Chen, CH Huang, YS Chu… - 2020 IEEE 9th Global …, 2020 - ieeexplore.ieee.org
Convolutional neural network (CNN) becomes more and more popular as it has
demonstrated great success in many visual content-oriented applications such as computer …

Novel activation function with pixelwise modeling capacity for lightweight neural network design

Y Liu, X Guo, K Tan, G Gong… - … and Computation: Practice …, 2023 - Wiley Online Library
The development of lightweight networks makes neural networks more efficient to be widely
applied to various tasks. Considering the deployment of hardware like edge devices and …

Trends in deep convolutional neural Networks architectures: A review

A Elhassouny, F Smarandache - 2019 International conference …, 2019 - ieeexplore.ieee.org
Deep convolutional Neural networks (CNN) has recognized much advances in recent years.
Many CNN models have been proposed in few years ago which focused by first on …

A Novel Lightweight Architecture of Deep Convolutional Neural Networks

B Liu, X Chen, Z Han, H Jia… - 2022 12th International …, 2022 - ieeexplore.ieee.org
Deep convolutional neural networks have achieved much success in many computer vision
tasks. However, a network has millions of parameters which limit its inference speed and …

Squishednets: Squishing squeezenet further for edge device scenarios via deep evolutionary synthesis

MJ Shafiee, F Li, B Chwyl, A Wong - arXiv preprint arXiv:1711.07459, 2017 - arxiv.org
While deep neural networks have been shown in recent years to outperform other machine
learning methods in a wide range of applications, one of the biggest challenges with …