检索结果-内蒙古大学图书馆

Carrying out CNN Channel Pruning in a White Box

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Zhang, Yuxin Lin, Mingbao Lin, Chia-Wen Chen, Jie Wu, Yongjian Tian, Yonghong Ji, Rongrong The Media Analytics and Computing Laboratory Department of Artificial Intelligence School of Informatics Xiamen University Xiamen361005 China The Youtu Laboratory Tencent Shanghai200233 China The Department of Electrical Engineering The Institute of Communications Engineering National Tsing Hua University Hsinchu30013 Taiwan The Peng Cheng Laboratory Shenzhen518000 China Department of Computer Science and Technology Peking University Beijing100871 China Institute of Artificial Intelligence Xiamen University Xiamen361005 China

Channel Pruning has been long studied to compress CNNs, which significantly reduces the overall computation. Prior works implement channel pruning in an unexplainable manner, which tends to reduce the final classification errors while failing to consider the internal influence of each channel. In this paper, we conduct channel pruning in a white box. Through deep visualization of feature maps activated by different channels, we observe that different channels have a varying contribution to different categories in image classification. Inspired by this, we choose to preserve channels contributing to most categories. Specifically, to model the contribution of each channel to differentiating categories, we develop a class-wise mask for each channel, implemented in a dynamic training manner w.r.t. the input image’s category. On the basis of the learned class-wise mask, we perform a global voting mechanism to remove channels with less category discrimination. Lastly, a fine-tuning process is conducted to recover the performance of the pruned model. To our best knowledge, it is the first time that CNN interpretability theory is considered to guide channel pruning. Extensive experiments on representative image classification tasks demonstrate the superiority of our White-Box over many state-of-the-arts. For instance, on CIFAR-10, it reduces 65.23% FLOPs with even 0.62% accuracy improvement for ResNet-110. On ILSVRC-2012, White-Box achieves a 45.6% FLOPs reduction with only a small loss of 0.83% in the top-1 accuracy for ResNet-50. Code is available at https://***/zyxxmu/White-Box. © 2021, CC BY.

关键词： Image classification

Correction to: Metaheuristics based tuning of robust PID controllers for controlling voltage and current on photonics and optics

学校读者我要写书评

暂无评论

Optical and Quantum Electronics 2023年第6期55卷 1-1页

作者： Aoudni, Yassine Kalra, Ashima Azhagumurugan, R. Ahmed, Mohammed Altaf Wanjari, Atul Krishnarao Singh, Bharat Bhardwaj, Arpit Department of Computers and Information Technology Faculty of Sciences and Arts Northern Border University Turaif Saudi Arabia Department of Electronics and Communication Engineering Chandigarh Engineering College Chandigarh India Department of Electrical and Electronics Engineering Sri Sai Ram Engineering College West Tambaram Chennai India Department of Computer Engineering College of Computer Engineering & Sciences Prince Sattam Bin Abdulaziz University Al-Kharj Saudi Arabia Sitaramji Chaudhari Science College Warud Dist-Amravati Warud India GLA University Mathura Mathura India BML Munjal University Kapriwas India

Effect of Annealing on the Structural, Optical Properties of Barium Titanate Nanoparticles and its Impact on Second Harmonic Generation

学校读者我要写书评

暂无评论

SSRN

SSRN 2023年

作者： Mayandi, Jeyanthinath Mahalakshmi, Selvaraj Venkatesan, Ragavendran Asokan, Vijay Shankar Alam, Mohammed Mujahid Pearce, Joshua M. Venkatachalapathy, Vishnukanthan Department of Physics R.D. Govt. Arts College Tamilnadu Sivaganga630561 India Department of Material Science School of Chemistry Madurai Kamaraj University Tamilnadu Madurai625 021 India Chalmers University of Technology Sweden King Khalid University Abha61413 Saudi Arabia Department of Chemistry College of Science King Khalid University Abha61413 Saudi Arabia Department of Electrical and Computer Engineering Western University LondonON Canada Department of Physics Centre for Materials Science and Nanotechnology University of Oslo P.O Box 1048 Blindern OsloNO-0316 Norway Department of Materials Science National Research Nuclear University "MEPhI" 31 Kashirskoe sh Moscow Russia

In this report, barium titanate (BaTiO3) nanoparticles were synthesized at 200°C by sol-gel hydrothermal process and annealed at five different temperatures from 100-500°C. The sample synthesized at 200°C exhibited distorted cubic structure with a mishmash of tetragonal and orthorhombic phase which was analyzed from XRD studies. To further empathize its characteristic features, the samples were annealed for various temperatures. The grain size and lattice parameters of the annealed samples were calculated from the XRD spectrum. When the annealing temperature increases a non-uniformity in the grain size and lattice parameters was observed in the BaTiO3 nanoparticles. XRD also reveals that there was phase transition from distorted cubic to tetragonal phase and this phase was stable for all the annealed samples. The morphology of annealed barium titanate nanoparticles was analyzed by scanning electron microscopy (SEM) and transmission electron microscopy (TEM) which specifies the presence of spheres and rods. Optical studies were carried out by UV-Vis, Photoluminescence and Raman Spectroscopy. The change in non-linear optical (NLO) activity of BaTiO3 nanoparticles were studied using second harmonic generation (SHG). Samples that possess phase distortion produced SHG as it lacks center of symmetry. Remarkably, the annealing process created an effective atmosphere for the formation of single crystalline tetragonal phase within 300-500°C, which is normally possible only above 800°C. © 2023, The Authors. All rights reserved.

关键词： Raman spectroscopy

Rethinking online action detection in untrimmed videos: A novel online evaluation protocol

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Baptista-Ríos, Marcos López-Sastre, Roberto J. Caba Heilbron, Fabian van Gemert, Jan C. Acevedo-Rodríguez, F. Javier Maldonado-Bascón, Saturnino GRAM Department of Signal Theory and Communications University of Alcalá Alcalá de Henares Spain Adobe Research Media Intelligence Lab Deep Learning Group Faculty of Electrical Engineering Mathematics and Computer Science Delft University of Technology Delft Netherlands

The Online Action Detection (OAD) problem needs to be revisited. Unlike traditional offline action detection approaches, where the evaluation metrics are clear and well established, in the OAD setting we find very few works and no consensus on the evaluation protocols to be used. In this work we propose to rethink the OAD scenario, clearly defining the problem itself and the main characteristics that the models which are considered online must comply with. We also introduce a novel metric: the Instantaneous Accuracy (IA). This new metric exhibits an online nature and solves most of the limitations of the previous metrics. We conduct a thorough experimental evaluation on 3 challenging datasets, where the performance of various baseline methods is compared to that of the state-of-the-art. Our results confirm the problems of the previous evaluation protocols, and suggest that an IA-based protocol is more adequate to the online scenario. The baselines models and a development kit with the novel evaluation protocol are publicly available here (https://***/gramuah/ia). Copyright © 2020, The Authors. All rights reserved.

关键词： computer vision

Optimization of multi parameters of WEDM using ANN based on principal component analysis for AA6063/B 4 C metal matrix composites

学校读者我要写书评

暂无评论

Materials Today: Proceedings 2023年

作者： R. Amuthakkannan K. Vijayalakshmi M. Kamarunisha Selva Ganesh Kumar Paul Ajithkumar P. Vikram Department of Mechanical and Industrial Engineering College of Engineering National University of Science and Technology Muscat Oman Department of Electrical and Communication Engineering College of Engineering National University of Science and Technology Muscat Oman Department of Computer Applications Dhanalakshmi Srinivasan College of Arts and Science for Women (Autonomous) Perambalur Tamil Nadu India Department of Mechanical Engineering Wollega University Ethiopia Department of Botany Bishop Heber College (Autonomous) Puthur Tiruchirappalli 620017 Tamil Nadu India Department of Mechanical Engineering St. Martin’s Engineering College Secunderabad Telengana India

Improved mechanical characteristics for composites using a linear low-density propylene (PP) matrix and a carbon fibre (CF) filler were the focus of this study. The material was fabricated by a hand layup process in an oven. Oxygen plasma treatment of the PP matrix enhanced adherence. Before being filtered and dried for manufacture, CF and PP were first combined with standard stirring, ultrasonication , and mechanical stirring. The highest tensile strength was achieved in plasma-treated propylene (PPP) with 10 wt% CF, with overall property performance increasing by 13.46 % comparison to non-PP with the same CF addition. Tensile strength was reduced from 19.4 MPa to 18.3 MPa when carbon fibers were added at 14 and 16 wt%. As a result of CF aggregation with plasma-treated and untreated PP, tensile strength (TS) was reduced. Better tensile qualities were seen in a factory setting with temperatures of 180 °C for 20 min. After plasma treatment , the PP/8% CF blend had a flexural strength (FS) of 26.19 MPa, which was higher than that of untreated PP by a significant margin.

关键词：

The aging effect in evolving scientific citation networks

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Hu, Feng Ma, Lin Zhan, Xiu-Xiu Zhou, Yinzuo Liu, Chuang Zhao, Haixing Zhang, Zi-Ke School of Computer Qinghai Normal University Xining810016 China Key Laboratory of Tibetan Information Processing Ministry of Education Xining810008 China Tibetan Information Processing and Machine Translation Key Laboratory of Qinghai Province Xining810008 China Alibaba Research Center for Complexity Sciences Hangzhou Normal University Hangzhou311121 China Faculty of Electrical Engineering Mathematics and Computer Science Delft University of Technology Delft2628 CD Netherlands College of Media and International Culture Zhejiang University Hangzhou310058 China

The study of citation networks is of interest to the scientific community. However, the underlying mechanism driving individual citation behavior remains imperfectly understood, despite the recent proliferation of quantitative research methods. Traditional network models normally use graph theory to consider articles as nodes and citations as pairwise relationships between them. In this paper, we propose an alternative evolutionary model based on hypergraph theory in which one hyperedge can have an arbitrary number of nodes, combined with an aging effect to reflect the temporal dynamics of scientific citation behavior. Both theoretical approximate solution and simulation analysis of the model are developed and validated using two benchmark datasets from different disciplines, i.e. publications of the American Physical Society (APS) and the Digital Bibliography & Library Project (DBLP). Further analysis indicates that the attraction of early publications will decay exponentially. Moreover, the experimental results show that the aging effect indeed has a significant influence on the description of collective citation patterns. Shedding light on the complex dynamics driving these mechanisms facilitates the understanding of the laws governing scientific evolution and the quantitative evaluation of scientific outputs. © 2021, CC BY.

关键词： Graph theory

Design of a Cryptographically Secure Pseudo Random Number Generator with Grammatical Evolution

学校读者我要写书评

暂无评论

Research Square

Research Square 2021年

作者： Ryan, Conor Kshirsagar, Meghana Vaidya, Gauri Cunningham, Andrew Sivaraman, R. Biocomputing and Developmental Systems Group Lero The Science Foundation Ireland Research Centre for Software Computer Science and Information System Department University of Limerick LimerickV94 T9PX Ireland Intel Research and Development Ireland Limited LeixlipW23 CX68 Ireland Department of Electronics Communication Engineering School of Electrical and Electronics Engineering Shanmugha Arts Science Technology and Research Academy Deemed to be University Thanjavur613401 India

This work investigates the potential of evolving an initial seed with Grammatical Evolution (GE), for the construction of cryptographically secure (CS) pseudo-random number generator (PRNG). We harness the flexibility of GE as an entropy source for returning initial seeds. The initial seeds returned by GE demonstrate an average entropy value of 7.920261600000001 which is extremely close to the ideal value of 8. The initial seed combined with our proposed approach, control_flow_incrementor, is used to construct both, GE-PRNG and GE-CSPRNG. The random numbers generated with CSPRNG meet the prescribed National Institute of Standards and technology (NIST) SP800-22 requirements. Monte Carlo simulations established the efficacy of the PRNG. The experimental setup was designed to estimate the value for pi, in which 100,000,000 random numbers were generated by our system and which resulted in returning the value of pi to 3.146564000, with a precision up to six decimal digits. The random numbers by GE-PRNG were compared against those generated by Python’s rand() function for sampling. The sampling results, when measured for accuracy against twenty-nine real world regression datasets, showed that GE-PRNG had less error when compared to Python’s rand() against the ground truths in seventeen of those, while there was no discernible difference in the remaining twelve. © 2021, CC BY.

关键词： Monte Carlo methods

Optical Thouless pumping transport and nonlinear switching in a topological low-dimensional discrete nematic liquid crystal array

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Jung, Pawel S. Parto, Midya Pyrialakos, Georgios G. Nasari, Hadiseh Rutkowska, Katarzyna Trippenbach, Marek Khajavikhan, Mercedeh Krolikowski, Wieslaw Christodoulides, Demetrios N. CREOL The College of Optics and Photonics University of Central Florida OrlandoFL32816 United States Faculty of Physics Warsaw University of Technology Warsaw Poland Ming Hsieh Department of Electrical and Computer Engineering University of Southern California Los AngelesCA90089 United States Faculty of Physics University of Warsaw Warsaw Poland Department of Physics & Astronomy Dornsife College of Letters Arts & Sciences University of Southern California Los AngelesCA90089 United States Laser Physics Centre Research School of Physics and Engineering Australian National University CanberraACT0200 Australia Science Program Texas A&M University at Qatar Doha Qatar

We theoretically investigate a Thouless pumping scheme in the 1D topological Su-Schrieffer-Heeger (SSH) model for single and multiple band-gaps systems when implemented in a discrete nematic liquid crystal arrangement. For an electrically controlled SSH waveguide array, we numerically demonstrate edge-to-edge light transport at low power levels. On the other hand, at higher powers, the transport is frustrated by light-induced nonlinear defect states, giving rise to robust all-optical switching. © 2022, CC BY.

关键词： Nematic liquid crystals

Quantization Games on Social Networks and Language Evolution

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Mani, Ankur Varshney, Lav R. Pentland, Alex Department of Industrial & Systems Engineering University of Minnesota MinneapolisMN55455 United States Coordinated Science Laboratory Department of Electrical and Computer Engineering University of Illinois at Urbana-Champaign UrbanaIL61801 United States Media Laboratory Massachusetts Institute of Technology CambridgeMA02139 United States

We consider a strategic network quantizer design setting where agents must balance fidelity in representing their local source distributions against their ability to successfully communicate with other connected agents. We study the problem as a network game and show existence of Nash equilibrium quantizers. For any agent, under Nash equilibrium, the word representing a given partition region is the conditional expectation of the mixture of local and social source probability distributions within the region. Since having knowledge of the original source of information in the network may not be realistic, we show that under certain conditions, the agents need not know the source origin and yet still settle on a Nash equilibrium using only the observed sources. Further, the network may converge to equilibrium through a distributed version of the Lloyd-Max algorithm. In contrast to traditional results in the evolution of language, we find several vocabularies may coexist in the Nash equilibrium, with each individual having exactly one of these vocabularies. The overlap between vocabularies is high for individuals that communicate frequently and have similar local sources. Finally, we argue that error in translation along a chain of communication does not grow if and only if the chain consists of agents with shared vocabulary. Numerical results are given. Copyright © 2020, The Authors. All rights reserved.

关键词： Game theory