Deep Tensor Capsule Network

Sun, Kun; Yuan, Liming; Xu, Haixia; Wen, Xianbin

doi:10.1109/access.2020.2996282

Cited by 21 publications

(7 citation statements)

References 9 publications

(31 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Each neuron of a capsule encodes spatial information, while the vector's length encodes the probability of the entity being present. While the first architecture proposed in [4] is composed of only three layers, recently deeper CapsNet models were proposed [13] [32]. The main components of a CapsNet are the following:…”

Section: B Convolutional and Capsule Network Hardwarementioning

confidence: 99%

RoHNAS: A Neural Architecture Search Framework With Conjoint Optimization for Adversarial Robustness and Hardware Efficiency of Convolutional and Capsule Networks

et al. 2022

View full text Add to dashboard Cite

Neural Architecture Search (NAS) algorithms aim at finding efficient Deep Neural Network (DNN) architectures for a given application under given system constraints. DNNs are computationallycomplex as well as vulnerable to adversarial attacks. In order to address multiple design objectives, we propose RoHNAS, a novel NAS framework that jointly optimizes for adversarial-robustness and hardwareefficiency of DNNs executed on specialized hardware accelerators. Besides the traditional convolutional DNNs, RoHNAS additionally accounts for complex types of DNNs such as Capsule Networks. For reducing the exploration time, RoHNAS analyzes and selects appropriate values of adversarial perturbation for each dataset to employ in the NAS flow. Extensive evaluations on multi -Graphics Processing Unit (GPU) -High Performance Computing (HPC) nodes provide a set of Pareto-optimal solutions, leveraging the tradeoff between the above-discussed design objectives. For example, a Pareto-optimal DNN for the CIFAR-10 dataset exhibits 86.07% accuracy, while having an energy of 38.63 mJ, a memory footprint of 11.85 MiB, and a latency of 4.47 ms.

show abstract

Section: B Convolutional and Capsule Network Hardwarementioning

confidence: 99%

RoHNAS: A Neural Architecture Search Framework With Conjoint Optimization for Adversarial Robustness and Hardware Efficiency of Convolutional and Capsule Networks

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Capsule networks suffer from expensive computational methods, yet numerous routing layers increase training costs and inference time because of the complexity of the network [29]. Researchers in [24] have, on the other hand, demonstrated that the prediction time is significantly shorter than that of other deep learning techniques.…”

Section: Cnn Is Currently Used In Many Applications and Has Shown Sat...mentioning

confidence: 99%

A pre-trained convolutional neural network with optimized capsule networks for chest X-rays COVID-19 diagnosis

et al. 2022

View full text Add to dashboard Cite

Coronavirus disease (COVID-19) is rapidly spreading worldwide. Recent studies show that radiological images contain accurate data for detecting the coronavirus. This paper proposes a pre-trained convolutional neural network (VGG16) with Capsule Neural Networks (CapsNet) to detect COVID-19 with unbalanced data sets. The CapsNet is proposed due to its ability to define features such as perspective, orientation, and size. Synthetic Minority Over-sampling Technique (SMOTE) was employed to ensure that new samples were generated close to the sample center, avoiding the production of outliers or changes in data distribution. As the results may change by changing capsule network parameters (Capsule dimensionality and routing number), the Gaussian optimization method has been used to optimize these parameters. Four experiments have been done, (1) CapsNet with the unbalanced data sets, (2) CapsNet with balanced data sets based on class weight, (3) CapsNet with balanced data sets based on SMOTE, and (4) CapsNet hyperparameters optimization with balanced data sets based on SMOTE. The performance has improved and achieved an accuracy rate of 96.58% and an F1- score of 97.08%, a competitive optimized model compared to other related models.

show abstract

“…As shown in [ 10 , 11 , 12 , 13 , 14 , 15 , 16 , 17 , 18 , 19 , 20 , 21 , 22 ], the network structure defines a discrete n -dimensional geometric space. In the introduced space for each individually selected packet flow, for which the conditions of QoS assurance will be obtained, the network will be described by a mixed bivalent tensor [ 19 , 20 , 21 ]:

where

is the tensor multiplication operator;…”

Section: Tensor Description Of the Network And Formalization Of Quality Of Service Assurance Conditionsmentioning

confidence: 99%

“…Due to the direct analogy of electrical and communication network processes, the tensor analysis apparatus applies to a wide range of traffic management and routing [ 10 , 11 , 12 , 13 , 14 , 15 , 16 ]. However, in terms of their structural and functional construction, communication networks are more complex systems than electrical circuits.…”

Section: Introductionmentioning

confidence: 99%

Research and Development of Delay-Sensitive Routing Tensor Model in IoT Core Networks

Lemeshko

Papán

Yeremenko

et al. 2021

Sensors

View full text Add to dashboard Cite

In the article, we present the research and development of an improved delay-sensitive routing tensor model for the core of the IoT network. The flow-based tensor model is considered within the coordinate system of interpolar paths and internal node pairs. The advantage of the presented model is the application for IoT architectures to ensure the Quality of Service under the parameters of bandwidth, average end-to-end delay, and the probability of packet loss. Hence, the technical task of delay-sensitive routing is formulated as the optimization problem together with constraints and conditions imposed on the corresponding routing variables. The system of optimality criteria is chosen for an investigation. Each selected criterion concerning the specifics of the demanded routing problem solution aims at the optimal use of available network resources and the improvement of QoS indicators, namely, average end-to-end delay. The analysis of the obtained routing solutions under different criteria is performed. Numerical research of the improved delay-sensitive routing tensor model allowed us to discover its features and proved the adequacy of the results for the multipath order of routing.

show abstract

Deep Tensor Capsule Network

Cited by 21 publications

References 9 publications

RoHNAS: A Neural Architecture Search Framework With Conjoint Optimization for Adversarial Robustness and Hardware Efficiency of Convolutional and Capsule Networks

RoHNAS: A Neural Architecture Search Framework With Conjoint Optimization for Adversarial Robustness and Hardware Efficiency of Convolutional and Capsule Networks

A pre-trained convolutional neural network with optimized capsule networks for chest X-rays COVID-19 diagnosis

Research and Development of Delay-Sensitive Routing Tensor Model in IoT Core Networks

Contact Info

Product

Resources

About