Machine Learning at Resource Constraint Edge Device Using Bonsai Algorithm

Naveen, Soumyalatha; Kounte, Manjunath R

doi:10.1109/icaecc50550.2020.9339514

Cited by 8 publications

(2 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Many existing research work focuses on developing DL applications on edge through various approaches such as DL training at edge, [13][14][15][16][17][18] DL inference on edge, 14,[19][20][21] or training on cloud or localhost 4 and inference. 22 Ultimately the objective is an accurate prediction with very less response time and memory footprint, even in the resource constraint devices. Various methods and techniques, such as model compression, pruning, and layer partitioning, are used to achieve low computational time and memory footprint.…”

Section: Background and Literature Surveymentioning

confidence: 99%

Memory optimization at Edge for Distributed Convolution Neural Network

Naveen

Kounte

2022

Trans Emerging Tel Tech

Self Cite

View full text Add to dashboard Cite

Internet of Things (IoT) edge intelligence has emerged by optimizing the deep learning (DL) models deployed on resource‐constraint devices for quick decision‐making. In addition, edge intelligence reduces network overload and latency by bringing intelligent analytics closer to the source. On the other hand, DL models need a lot of computing resources. As a result, they have high computational workloads and memory footprint, making it impractical to deploy and execute on IoT edge devices with limited capabilities. In addition, existing layer‐based partitioning methods generate many intermediate results, resulting in a huge memory footprint. In this article, we propose a framework to provide a comprehensive solution that enables the deployment of convolutional neural networks (CNNs) onto distributed IoT devices for faster inference and reduced memory footprint. This framework considers a pretrained YOLOv2 model, and a weight pruning technique is applied to the pre‐trained model to reduce the number of non‐contributing parameters. We use the fused layer partitioning method to vertically partition the fused layers of the CNN and then distribute the partition among the edge devices to process the input. In our experiment, we have considered multiple Raspberry Pi as edge devices. Raspberry Pi with a neural computing stick is a gateway device to combine the results from various edge devices and get the final output. Our proposed model achieved inference latency of 5 to ∼$$ \sim $$7 seconds for 3prefix×3$$ 3\times 3 $$ to 5prefix×5$$ 5\times 5 $$ fused layer partitioning for five devices with a 9% improvement in memory footprint.

show abstract

Section: Background and Literature Surveymentioning

confidence: 99%

Memory optimization at Edge for Distributed Convolution Neural Network

Naveen

Kounte

2022

Trans Emerging Tel Tech

Self Cite

View full text Add to dashboard Cite

show abstract

“…However, real-time embedded system-based applications or smart devices cannot use CNN-based models due to their high computational and storage requirements. Due to privacy, security, latency, communication bandwidth and memory requirements, processing the data through AI-enabled embedded devices supports processing locally [8] close to the sensor. Although a lot of work focuses on developing edge intelligence; still, the adoption of CNN on embedded devices is challenging due to the high computing resource requirements.…”

Section: Introductionmentioning

confidence: 99%

Compact optimized deep learning model for edge: a review

Naveen,

Kounte

2023

IJECE

View full text Add to dashboard Cite

<p>Most real-time computer vision applications, such as pedestrian detection, augmented reality, and virtual reality, heavily rely on convolutional neural networks (CNN) for real-time decision support. In addition, edge intelligence is becoming necessary for low-latency real-time applications to process the data at the source device. Therefore, processing massive amounts of data impact memory footprint, prediction time, and energy consumption, essential performance metrics in machine learning based internet of things (IoT) edge clusters. However, deploying deeper, dense, and hefty weighted CNN models on resource-constraint embedded systems and limited edge computing resources, such as memory, and battery constraints, poses significant challenges in developing the compact optimized model. Reducing the energy consumption in edge IoT networks is possible by reducing the computation and data transmission between IoT devices and gateway devices. Hence there is a high demand for making energy-efficient deep learning models for deploying on edge devices. Furthermore, recent studies show that smaller compressed models achieve significant performance compared to larger deep-learning models. This review article focuses on state-of-the-art techniques of edge intelligence, and we propose a new research framework for designing a compact optimized deep learning (DL) model deployment on edge devices.</p>

show abstract

Intelligence and Cognitive Computing at the Edge for IoT: Architecture, Challenges, and Applications

Kusuma

Veena

et al. 2022

IoT Based Smart Applications

View full text Add to dashboard Cite

Machine Learning at Resource Constraint Edge Device Using Bonsai Algorithm

Cited by 8 publications

References 13 publications

Memory optimization at Edge for Distributed Convolution Neural Network

Memory optimization at Edge for Distributed Convolution Neural Network

Compact optimized deep learning model for edge: a review

Intelligence and Cognitive Computing at the Edge for IoT: Architecture, Challenges, and Applications

Contact Info

Product

Resources

About