Enabling Deep Learning for All-in EDGE paradigm

• URL: http://arxiv.org/abs/2204.03326v1
• Date: Thu, 7 Apr 2022 09:47:10 GMT
• Title: Enabling Deep Learning for All-in EDGE paradigm
• Authors: Praveen Joshi, Haithem Afli, Mohammed Hasanuzzaman, Chandra Thapa, and Ted Scully
• Abstract summary: Deep Learning models have been widely investigated, and they have demonstrated significant performance on non-trivial tasks. Deep Learning in the edge paradigm, such as device-cloud integrated platforms, is required to leverage its superior performance. This paper investigates Deep Learning at the edge, its architecture, enabling technologies, and model adaption techniques.
• Score: 4.055662817794178
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Deep Learning-based models have been widely investigated, and they have demonstrated significant performance on non-trivial tasks such as speech recognition, image processing, and natural language understanding. However, this is at the cost of substantial data requirements. Considering the widespread proliferation of edge devices (e.g. Internet of Things devices) over the last decade, Deep Learning in the edge paradigm, such as device-cloud integrated platforms, is required to leverage its superior performance. Moreover, it is suitable from the data requirements perspective in the edge paradigm because the proliferation of edge devices has resulted in an explosion in the volume of generated and collected data. However, there are difficulties due to other requirements such as high computation, high latency, and high bandwidth caused by Deep Learning applications in real-world scenarios. In this regard, this survey paper investigates Deep Learning at the edge, its architecture, enabling technologies, and model adaption techniques, where edge servers and edge devices participate in deep learning training and inference. For simplicity, we call this paradigm the All-in EDGE paradigm. Besides, this paper presents the key performance metrics for Deep Learning at the All-in EDGE paradigm to evaluate various deep learning techniques and choose a suitable design. Moreover, various open challenges arising from the deployment of Deep Learning at the All-in EDGE paradigm are identified and discussed.

Related papers

• A Survey on Design Methodologies for Accelerating Deep Learning on Heterogeneous Architectures [9.982620766142345]
  The need for efficient hardware accelerators has become more pressing to design heterogeneous HPC platforms. Several methodologies and tools have been proposed to design accelerators for Deep Learning. This survey provides a holistic review of the most influential design methodologies and EDA tools proposed in recent years to implement Deep Learning accelerators.
  arXiv  Detail & Related papers  (2023-11-29T17:10:16Z)
• Computation-efficient Deep Learning for Computer Vision: A Survey [121.84121397440337]
  Deep learning models have reached or even exceeded human-level performance in a range of visual perception tasks. Deep learning models usually demand significant computational resources, leading to impractical power consumption, latency, or carbon emissions in real-world scenarios. New research focus is computationally efficient deep learning, which strives to achieve satisfactory performance while minimizing the computational cost during inference.
  arXiv  Detail & Related papers  (2023-08-27T03:55:28Z)
• EdgeConvEns: Convolutional Ensemble Learning for Edge Intelligence [0.0]
  Deep edge intelligence aims to deploy deep learning models that demand computationally expensive training in the edge network with limited computational power. This study proposes a convolutional ensemble learning approach, coined EdgeConvEns, that facilitates training heterogeneous weak models on edge and learning to ensemble them where data on edge are heterogeneously distributed.
  arXiv  Detail & Related papers  (2023-07-25T20:07:32Z)
• A Threefold Review on Deep Semantic Segmentation: Efficiency-oriented, Temporal and Depth-aware design [77.34726150561087]
  We conduct a survey on the most relevant and recent advances in Deep Semantic in the context of vision for autonomous vehicles. Our main objective is to provide a comprehensive discussion on the main methods, advantages, limitations, results and challenges faced from each perspective.
  arXiv  Detail & Related papers  (2023-03-08T01:29:55Z)
• Deep networks for system identification: a Survey [56.34005280792013]
  System identification learns mathematical descriptions of dynamic systems from input-output data. Main aim of the identified model is to predict new data from previous observations. We discuss architectures commonly adopted in the literature, like feedforward, convolutional, and recurrent networks.
  arXiv  Detail & Related papers  (2023-01-30T12:38:31Z)
• Design Automation for Fast, Lightweight, and Effective Deep Learning Models: A Survey [53.258091735278875]
  This survey covers studies of design automation techniques for deep learning models targeting edge computing. It offers an overview and comparison of key metrics that are used commonly to quantify the proficiency of models in terms of effectiveness, lightness, and computational costs. The survey proceeds to cover three categories of the state-of-the-art of deep model design automation techniques.
  arXiv  Detail & Related papers  (2022-08-22T12:12:43Z)
• Bringing AI To Edge: From Deep Learning's Perspective [7.308396023489246]
  Edge computing and artificial intelligence (AI) are gradually intersecting to build a novel system, called edge intelligence. One of these challenges is the textitcomputational gap between computation-intensive deep learning algorithms and less-capable edge systems. This paper surveys the representative and latest deep learning techniques that are useful for edge intelligence systems.
  arXiv  Detail & Related papers  (2020-11-25T12:07:21Z)
• State-of-the-art Techniques in Deep Edge Intelligence [0.0]
  Edge Intelligence (EI) has quickly emerged as a powerful alternative to enable learning using the concepts of Edge Computing. In this article, we provide an overview of the major constraints in operationalizing DEI.
  arXiv  Detail & Related papers  (2020-08-03T12:17:23Z)
• Accurate RGB-D Salient Object Detection via Collaborative Learning [101.82654054191443]
  RGB-D saliency detection shows impressive ability on some challenge scenarios. We propose a novel collaborative learning framework where edge, depth and saliency are leveraged in a more efficient way.
  arXiv  Detail & Related papers  (2020-07-23T04:33:36Z)
• Knowledge Distillation: A Survey [87.51063304509067]
  Deep neural networks have been successful in both industry and academia, especially for computer vision tasks. It is a challenge to deploy these cumbersome deep models on devices with limited resources. Knowledge distillation effectively learns a small student model from a large teacher model.
  arXiv  Detail & Related papers  (2020-06-09T21:47:17Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.