Articles with "cnn inference" as a keyword



Photo by visuals from unsplash

cuConv: CUDA implementation of convolution for CNN inference

Sign Up to like & get
recommendations!
Published in 2022 at "Cluster Computing"

DOI: 10.1007/s10586-021-03494-y

Abstract: Convolutions are the core operation of deep learning applications based on Convolutional Neural Networks (CNNs). Current GPU architectures are highly efficient for training and deploying deep CNNs, and are largely used in production. State–of–the–art implementations,… read more here.

Keywords: implementation; implementation convolution; cnn inference; convolution ... See more keywords
Photo from wikipedia

Enhancing Distributed In-Situ CNN Inference in the Internet of Things

Sign Up to like & get
recommendations!
Published in 2022 at "IEEE Internet of Things Journal"

DOI: 10.1109/jiot.2022.3176408

Abstract: Convolutional neural networks (CNNS) enable machines to view the world as humans and become increasing prevalent for Internet of Things (IoT) applications. Instead of streaming the raw data to the cloud and executing CNN inference… read more here.

Keywords: distributed situ; inference; internet things; situ cnn ... See more keywords
Photo from wikipedia

Automated Exploration and Implementation of Distributed CNN Inference at the Edge

Sign Up to like & get
recommendations!
Published in 2023 at "IEEE Internet of Things Journal"

DOI: 10.1109/jiot.2023.3237572

Abstract: For model inference of convolutional neural networks (CNNs), we nowadays witness a shift from the Cloud to the Edge. Unfortunately, deploying and inferring large, compute- and memory-intensive CNNs on Internet of Things devices at the… read more here.

Keywords: inference; edge devices; exploration; distributed cnn ... See more keywords
Photo by erwanhesry from unsplash

Multiplication Through a Single Look-Up-Table (LUT) in CNN Inference Computation

Sign Up to like & get
recommendations!
Published in 2021 at "IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems"

DOI: 10.1109/tcad.2021.3095825

Abstract: Parameter quantization with lower bit-width is the common approach to reduce the computation loads in CNN inference. With the parameters being replaced by fixed-width binaries, multiplication operations can be replaced by the look-up-table (LUT), where… read more here.

Keywords: table lut; cnn inference; computation; multiplication ... See more keywords