Communication-efficient edge AI: Algorithms and systems
Artificial intelligence (AI) has achieved remarkable breakthroughs in a wide range of fields,
ranging from speech processing, image classification to drug discovery. This is driven by the …
ranging from speech processing, image classification to drug discovery. This is driven by the …
A comprehensive review of model compression techniques in machine learning
PV Dantas, W Sabino da Silva Jr, LC Cordeiro… - Applied …, 2024 - Springer
This paper critically examines model compression techniques within the machine learning
(ML) domain, emphasizing their role in enhancing model efficiency for deployment in …
(ML) domain, emphasizing their role in enhancing model efficiency for deployment in …
Edge-AI-driven framework with efficient mobile network design for facial expression recognition
Facial Expression Recognition (FER) in the wild poses significant challenges due to realistic
occlusions, illumination, scale, and head pose variations of the facial images. In this article …
occlusions, illumination, scale, and head pose variations of the facial images. In this article …
Distredge: Speeding up convolutional neural network inference on distributed edge devices
As the number of edge devices with computing resources (eg, embedded GPUs, mobile
phones, and laptops) in-creases, recent studies demonstrate that it can be beneficial to col …
phones, and laptops) in-creases, recent studies demonstrate that it can be beneficial to col …
Compacting deep neural networks for Internet of Things: Methods and applications
Deep neural networks (DNNs) have shown great success in completing complex tasks.
However, DNNs inevitably bring high computational cost and storage consumption due to …
However, DNNs inevitably bring high computational cost and storage consumption due to …
Low latency deep learning inference model for distributed intelligent IoT edge clusters
Edge computing is a new paradigm enabling intelligent applications for the Internet of
Things (IoT) using mobile, low-cost IoT devices embedded with data analytics. Due to the …
Things (IoT) using mobile, low-cost IoT devices embedded with data analytics. Due to the …
Distributed deep convolutional neural networks for the internet-of-things
Severe constraints on memory and computation characterizing the Internet-of-Things (IoT)
units may prevent the execution of Deep Learning (DL)-based solutions, which typically …
units may prevent the execution of Deep Learning (DL)-based solutions, which typically …
Self-aware distributed deep learning framework for heterogeneous IoT edge devices
Implementing artificial intelligence (AI) in the Internet of Things (IoT) involves a move from
the cloud to the heterogeneous and low-power edge, following an urgent demand for …
the cloud to the heterogeneous and low-power edge, following an urgent demand for …
Memory optimization at edge for distributed convolution neural network
Abstract Internet of Things (IoT) edge intelligence has emerged by optimizing the deep
learning (DL) models deployed on resource‐constraint devices for quick decision‐making …
learning (DL) models deployed on resource‐constraint devices for quick decision‐making …
Communication-aware DNN pruning
We propose a Communication-aware Pruning (CaP) algorithm, a novel distributed inference
framework for distributing DNN computations across a physical network. Departing from …
framework for distributing DNN computations across a physical network. Departing from …