اشترك بالحزمة الذهبية واحصل على وصول غير محدود شمرا أكاديميا
تسجيل مستخدم جديدDeepEdgeBench: Benchmarking Deep Neural Networks on Edge Devices
118
0
0.0
(
0
)
اسأل ChatGPT حول البحث
ﻻ يوجد ملخص باللغة العربية
EdgeAI (Edge computing based Artificial Intelligence) has been most actively researched for the last few years to handle variety of massively distributed AI applications to meet up the strict latency requirements. Meanwhile, many companies have released edge devices with smaller form factors (low power consumption and limited resources) like the popular Raspberry Pi and Nvidias Jetson Nano for acting as compute nodes at the edge computing environments. Although the edge devices are limited in terms of computing power and hardware resources, they are powered by accelerators to enhance their performance behavior. Therefore, it is interesting to see how AI-based Deep Neural Networks perform on such devices with limited resources. In this work, we present and compare the performance in terms of inference time and power consumption of the four Systems on a Chip (SoCs): Asus Tinker Edge R, Raspberry Pi 4, Google Coral Dev Board, Nvidia Jetson Nano, and one microcontroller: Arduino Nano 33 BLE, on different deep learning models and frameworks. We also provide a method for measuring power consumption, inference time and accuracy for the devices, which can be easily extended to other devices. Our results showcase that, for Tensorflow based quantized model, the Google Coral Dev Board delivers the best performance, both for inference time and power consumption. For a low fraction of inference computation time, i.e. less than 29.3% of the time for MobileNetV2, the Jetson Nano performs faster than the other devices.
قيم البحث
اقرأ أيضاً
Analog hardware implemented deep learning models are promising for computation and energy constrained systems such as edge computing devices. However, the analog nature of the device and the associated many noise sources will cause changes to the val
ue of the weights in the trained deep learning models deployed on such devices. In this study, systematic evaluation of the inference performance of trained popular deep learning models for image classification deployed on analog devices has been carried out, where additive white Gaussian noise has been added to the weights of the trained models during inference. It is observed that deeper models and models with more redundancy in design such as VGG are more robust to the noise in general. However, the performance is also affected by the design philosophy of the model, the detailed structure of the model, the exact machine learning task, as well as the datasets.
We focus on the election manipulation problem through social influence, where a manipulator exploits a social network to make her most preferred candidate win an election. Influence is due to information in favor of and/or against one or multiple can
didates, sent by seeds and spreading through the network according to the independent cascade model. We provide a comprehensive study of the election control problem, investigating two forms of manipulations: seeding to buy influencers given a social network, and removing or adding edges in the social network given the seeds and the information sent. In particular, we study a wide range of cases distinguishing for the number of candidates or the kind of information spread over the network. Our main result is positive for democracy, and it shows that the election manipulation problem is not affordable in the worst-case except for trivial classes of instances, even when one accepts to approximate the margin of victory. In the case of seeding, we also show that the manipulation is hard even if the graph is a line and that a large class of algorithms, including most of the approaches recently adopted for social-influence problems, fail to compute a bounded approximation even on elementary networks, as undirected graphs with every node having a degree at most two or directed trees. In the case of edge removal or addition, our hardness results also apply to the basic case of social influence maximization/minimization. In contrast, the hardness of election manipulation holds even when the manipulator has an unlimited budget, being allowed to remove or add an arbitrary number of edges.
We present a new approach to learning for planning, where knowledge acquired while solving a given set of planning problems is used to plan faster in related, but new problem instances. We show that a deep neural network can be used to learn and repr
esent a emph{generalized reactive policy} (GRP) that maps a problem instance and a state to an action, and that the learned GRPs efficiently solve large classes of challenging problem instances. In contrast to prior efforts in this direction, our approach significantly reduces the dependence of learning on handcrafted domain knowledge or feature selection. Instead, the GRP is trained from scratch using a set of successful execution traces. We show that our approach can also be used to automatically learn a heuristic function that can be used in directed search algorithms. We evaluate our approach using an extensive suite of experiments on two challenging planning problem domains and show that our approach facilitates learning complex decision making policies and powerful heuristic functions with minimal human input. Videos of our results are available at goo.gl/Hpy4e3.
Graph Neural Networks (GNNs) have recently shown to be powerful tools for representing and analyzing graph data. So far GNNs is becoming an increasingly critical role in software engineering including program analysis, type inference, and code repres
entation. In this paper, we introduce GraphGallery, a platform for fast benchmarking and easy development of GNNs based software. GraphGallery is an easy-to-use platform that allows developers to automatically deploy GNNs even with less domain-specific knowledge. It offers a set of implementations of common GNN models based on mainstream deep learning frameworks. In addition, existing GNNs toolboxes such as PyG and DGL can be easily incorporated into the platform. Experiments demonstrate the reliability of implementations and superiority in fast coding. The official source code of GraphGallery is available at https://github.com/EdisonLeeeee/GraphGallery and a demo video can be found at https://youtu.be/mv7Zs1YeaYo.
In a previous work we have detailed the requirements to obtain a maximal performance benefit by implementing fully connected deep neural networks (DNN) in form of arrays of resistive devices for deep learning. This concept of Resistive Processing Uni
t (RPU) devices we extend here towards convolutional neural networks (CNNs). We show how to map the convolutional layers to RPU arrays such that the parallelism of the hardware can be fully utilized in all three cycles of the backpropagation algorithm. We find that the noise and bound limitations imposed due to analog nature of the computations performed on the arrays effect the training accuracy of the CNNs. Noise and bound management techniques are presented that mitigate these problems without introducing any additional complexity in the analog circuits and can be addressed by the digital circuits. In addition, we discuss digitally programmable update management and device variability reduction techniques that can be used selectively for some of the layers in a CNN. We show that combination of all those techniques enables a successful application of the RPU concept for training CNNs. The techniques discussed here are more general and can be applied beyond CNN architectures and therefore enables applicability of RPU approach for large class of neural network architectures.
الأسئلة المقترحة
سجل دخول لتتمكن من نشر تعليقات
التعليقات
جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
