Exploring Deep Neural Networks on Edge TPU

• URL: http://arxiv.org/abs/2110.08826v2
• Date: Wed, 20 Oct 2021 05:54:46 GMT
• Title: Exploring Deep Neural Networks on Edge TPU
• Authors: Seyedehfaezeh Hosseininoorbin, Siamak Layeghy, Brano Kusy, Raja Jurdak, Marius Portmann
• Abstract summary: This paper explores the performance of Google's Edge TPU on feed forward neural networks. We compare the energy efficiency of Edge TPU with that of widely-used embedded CPU ARM Cortex-A53.
• Score: 2.9573904824595614
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: This paper explores the performance of Google's Edge TPU on feed forward neural networks. We consider Edge TPU as a hardware platform and explore different architectures of deep neural network classifiers, which traditionally has been a challenge to run on resource constrained edge devices. Based on the use of a joint-time-frequency data representation, also known as spectrogram, we explore the trade-off between classification performance and the energy consumed for inference. The energy efficiency of Edge TPU is compared with that of widely-used embedded CPU ARM Cortex-A53. Our results quantify the impact of neural network architectural specifications on the Edge TPU's performance, guiding decisions on the TPU's optimal operating point, where it can provide high classification accuracy with minimal energy consumption. Also, our evaluations highlight the crossover in performance between the Edge TPU and Cortex-A53, depending on the neural network specifications. Based on our analysis, we provide a decision chart to guide decisions on platform selection based on the model parameters and context.

Related papers

• Task-Oriented Real-time Visual Inference for IoVT Systems: A Co-design Framework of Neural Networks and Edge Deployment [61.20689382879937]
  Task-oriented edge computing addresses this by shifting data analysis to the edge. Existing methods struggle to balance high model performance with low resource consumption. We propose a novel co-design framework to optimize neural network architecture.
  arXiv  Detail & Related papers  (2024-10-29T19:02:54Z)
• Energy efficiency in Edge TPU vs. embedded GPU for computer-aided medical imaging segmentation and classification [0.9728436272434581]
  We use glaucoma diagnosis based on color fundus images as an example to show the possibility of performing segmentation and classification in real time on embedded boards. Memory limitations and low processing capabilities of embedded accelerated systems (EAS) limit their use for deep network-based system training. We evaluate the timing and energy performance of two EAS equipped with Machine Learning (ML) accelerators executing an example diagnostic tool developed in a previous work.
  arXiv  Detail & Related papers  (2023-11-20T09:38:56Z)
• Exploration of TPUs for AI Applications [0.0]
  Processing Units (TPUs) are specialized hardware accelerators for deep learning developed by Google. This paper aims to explore TPUs in cloud and edge computing focusing on its applications in AI.
  arXiv  Detail & Related papers  (2023-09-16T07:58:05Z)
• FLEdge: Benchmarking Federated Machine Learning Applications in Edge Computing Systems [61.335229621081346]
  Federated Learning (FL) has become a viable technique for realizing privacy-enhancing distributed deep learning on the network edge. In this paper, we propose FLEdge, which complements existing FL benchmarks by enabling a systematic evaluation of client capabilities.
  arXiv  Detail & Related papers  (2023-06-08T13:11:20Z)
• PCBDet: An Efficient Deep Neural Network Object Detection Architecture for Automatic PCB Component Detection on the Edge [48.7576911714538]
  PCBDet is an attention condenser network design that provides state-of-the-art inference throughput. It achieves superior PCB component detection performance compared to other state-of-the-art efficient architecture designs.
  arXiv  Detail & Related papers  (2023-01-23T04:34:25Z)
• Braille Letter Reading: A Benchmark for Spatio-Temporal Pattern Recognition on Neuromorphic Hardware [50.380319968947035]
  Recent deep learning approaches have reached accuracy in such tasks, but their implementation on conventional embedded solutions is still computationally very and energy expensive. We propose a new benchmark for computing tactile pattern recognition at the edge through letters reading. We trained and compared feed-forward and recurrent spiking neural networks (SNNs) offline using back-propagation through time with surrogate gradients, then we deployed them on the Intel Loihimorphic chip for efficient inference. Our results show that the LSTM outperforms the recurrent SNN in terms of accuracy by 14%. However, the recurrent SNN on Loihi is 237 times more energy
  arXiv  Detail & Related papers  (2022-05-30T14:30:45Z)
• An Adaptive Device-Edge Co-Inference Framework Based on Soft Actor-Critic [72.35307086274912]
  High-dimension parameter model and large-scale mathematical calculation restrict execution efficiency, especially for Internet of Things (IoT) devices. We propose a new Deep Reinforcement Learning (DRL)-Soft Actor Critic for discrete (SAC-d), which generates the emphexit point, emphexit point, and emphcompressing bits by soft policy iterations. Based on the latency and accuracy aware reward design, such an computation can well adapt to the complex environment like dynamic wireless channel and arbitrary processing, and is capable of supporting the 5G URL
  arXiv  Detail & Related papers  (2022-01-09T09:31:50Z)
• Deep Learning on Edge TPUs [0.0]
  I review the Edge TPU platform, the tasks that have been accomplished using the Edge TPU, and which steps are necessary to deploy a model to the Edge TPU hardware. The Edge TPU is not only capable of tackling common computer vision tasks, but also surpasses other hardware accelerators. Co-embedding the Edge TPU in cameras allows a seamless analysis of primary data.
  arXiv  Detail & Related papers  (2021-08-31T10:23:37Z)
• Exploring Edge TPU for Network Intrusion Detection in IoT [2.8873930745906957]
  This paper explores Google's Edge TPU for implementing a practical network intrusion detection system (NIDS) at the edge of IoT, based on a deep learning approach. Various scaled model sizes of two major deep neural network architectures are used to investigate these three metrics. The performance of the Edge TPU-based implementation is compared with that of an energy efficient embedded CPU (ARM Cortex A53)
  arXiv  Detail & Related papers  (2021-03-30T12:43:57Z)
• An Evaluation of Edge TPU Accelerators for Convolutional Neural Networks [2.7584363116322863]
  Edge TPUs are accelerators for low-power, edge devices and are widely used in various Google products such as Coral and Pixel devices. We extensively evaluate three classes of Edge TPUs, covering different computing ecosystems, that are either currently deployed in Google products or are the product pipeline. We present our efforts in developing high-accuracy learned machine learning models to estimate the major performance metrics of accelerators.
  arXiv  Detail & Related papers  (2021-02-20T19:25:09Z)
• Towards AIOps in Edge Computing Environments [60.27785717687999]
  This paper describes the system design of an AIOps platform which is applicable in heterogeneous, distributed environments. It is feasible to collect metrics with a high frequency and simultaneously run specific anomaly detection algorithms directly on edge devices.
  arXiv  Detail & Related papers  (2021-02-12T09:33:00Z)

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.