检索结果-内蒙古大学图书馆

On Exact Space-Depth Trade-Offs in Multi-Controlled Toffoli Decomposition

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Dutta, Suman Wang, Siyi Baksi, Anubhab Chattopadhyay, Anupam Maitra, Subhamoy College of Computing & Data Science Nanyang Technological University Singapore School of Physical & Mathematical Sciences Nanyang Technological University Singapore Applied Statistics Unit Indian Statistical Institute Kolkata India

In this paper, we consider the optimized implementation of Multi Controlled Toffoli (MCT) using the Clifford + T gate sets. While there are several recent works in this direction, here we explicitly quantify the trade-off (with concrete formulae) between the Toffoli depth (this means the depth using the classical 2-controlled Toffoli) of the n-controlled Toffoli (hereform we will tell n-MCT) and the number of clean ancilla qubits. Additionally, we achieve a reduced Toffoli depth (and consequently, T-depth), which is an extension of the technique introduced by Khattar et al. (2024). In terms of a negative result, we first show that using such conditionally clean ancillae techniques, Toffoli depth can never achieve exactly ⌈log2 n⌉, though it remains of the same order. This highlights the limitation of the techniques exploiting conditionally clean ancillae [Nie et al., 2024, Khattar et al., 2024]. Then we prove that, in a more general setup, the T-Depth in the Clifford + T decomposition, via Toffoli gates, is lower bounded by ⌈log2 n⌉, and this bound is achieved following the complete binary tree structure. Since the (2-controlled) Toffoli gate can further be decomposed using Clifford + T, various methodologies are explored too in this regard for trade-off related *** Codes 81P65 Copyright © 2025, The Authors. All rights reserved.

关键词： Trees (mathematics)

Classified Recognition Method for Analyzing User Sentiments Using Social Media Posts 9

学校读者我要写书评

暂无评论

Classified Recognition Method for Analyzing User Sentiments ...

9th International Conference on science, Technology, Engineering and Mathematics, ICONSTEM 2024

作者： Ramesh, S. Vishnupriya, K. Anandaraj, A. Satheesh, N.P. Richard, Titus Bohra, Dixit Dutt College of Engineering & Technology Srm Institute of Science And Technology Department of Computing Technologies Tamilnadu Kattankulathur India Karpagam College of Engineering Department of Artificial Intelligence And Data Science Tamilnadu Coimbatore India Sri Eshwar College of Engineering Department of Cse Tamilnadu Coimbatore India Bannari Amman Institute of Technology Department of Ai&ds Tamilnadu Erode India Saveetha School of Engineering Saveetha Institute of Medical And Technical Sciences Saveetha University Department of Biosciences Chennai India Iit Jodhpur Department of Cse Rajasthan 34200 India

ISBN: (纸本)9798350365092

Social media texts and posts are analyzed through modern computing and artificial intelligence systems to detect user sentiments. The severity of the words and their related activities are analyzed to detect the user sentiments. In this paper, a Classified Sentiment Recognition Method (CSRM) is introduced. The proposed method utilizes deep learning to identify and classify sentiments using their associated words. Using the associated labels, deep learning trains the context and occurrence of the texts/ posts to detect precise sentiments. Thus the learning steps are induced with label, context, and occurrence-based training to improve the sentiment detection and type classification. This proposed method is verified using recognition accuracy, classification rate, and recognition error. © 2024 IEEE.

关键词： Social networking (online)

CausalDiff: Causality-Inspired Disentanglement via Diffusion Model for Adversarial Defense

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zhang, Mingkun Bi, Keping Chen, Wei Chen, Quanrun Guo, Jiafeng Cheng, Xueqi CAS Key Laboratory of AI Safety Institute of Computing Technology CAS China Key Laboratory of Network Data Science and Technology Institute of Computing Technology CAS China School of Statistics University of International Business and Economics China CAS stands for Chinese Academy of Sciences China

Despite ongoing efforts to defend neural classifiers from adversarial attacks, they remain vulnerable, especially to unseen attacks. In contrast, humans are difficult to be cheated by subtle manipulations, since we make judgments only based on essential factors. Inspired by this observation, we attempt to model label generation with essential label-causative factors and incorporate label-non-causative factors to assist data generation. For an adversarial example, we aim to discriminate the perturbations as non-causative factors and make predictions only based on the label-causative factors. Concretely, we propose a casual diffusion model (CausalDiff) that adapts diffusion models for conditional data generation and disentangles the two types of casual factors by learning towards a novel casual information bottleneck objective. Empirically, CausalDiff has significantly outperformed state-of-the-art defense methods on various unseen attacks, achieving an average robustness of 86.39% (+4.01%) on CIFAR-10, 56.25% (+3.13%) on CIFAR-100, and 82.62% (+4.93%) on GTSRB (German Traffic Sign Recognition Benchmark). The code is available at https://***/TMLResearchGroup-CAS/CausalDiff. Copyright © 2024, The Authors. All rights reserved.

关键词： Traffic signs

Displacement-Sparse Neural Optimal Transport

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Chen, Peter Xie, Yue Zhang, Qingpeng Department of Mathematics Columbia University New York United States HKU Musketeers Foundation Institute of Data Science Hong Kong HKU Shanghai Intelligent Computing Research Center Shanghai China

Optimal Transport (OT) theory seeks to determine the map T : X → Y that transports a source measure P to a target measure Q, minimizing the cost c(x, T(x)) between x and its image T(x). Building upon the Input Convex Neural Network OT solver (Makkuva et al., 2020;Amos et al., 2017) and incorporating the concept of displacement-sparse maps (Cuturi et al., 2023), we introduce a sparsity penalty into the minimax Wasserstein formulation, promote sparsity in displacement vectors ∆(x):= T(x) − x, and enhance the interpretability of the resulting map. However, increasing sparsity often reduces feasibility, causing T#(P) to deviate more significantly from the target measure. In low-dimensional settings, we propose a heuristic framework to balance the tradeoff between sparsity and feasibility by dynamically adjusting the sparsity intensity parameter during training. For high-dimensional settings, we directly constrain the dimensionality of displacement vectors by enforcing dim(∆(x)) ≤ l, where l d. Among maps satisfying this constraint, we aim to identify the most feasible one. This goal can be effectively achieved by adapting our low-dimensional heuristic framework without resorting to dimensionality reduction. We validate our method on both synthesized sc-RNA and real 4i cell perturbation datasets, demonstrating improvements over existing methods. © 2025, CC BY.

关键词： Dimensionality reduction

Quantum Machine Learning A Hands-on Tutorial for Machine Learning Practitioners and Researchers

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Du, Yuxuan Wang, Xinbiao Guo, Naixu Yu, Zhan Qian, Yang Zhang, Kaining Hsieh, Min-Hsiu Rebentrost, Patrick Tao, Dacheng College of Computing and Data Science Nanyang Technological University 639798 Singapore Centre for Quantum Technologies National University of Singapore 117543 Singapore Hon Hai Research Institute Taipei114 Taiwan

This tutorial intends to introduce readers with a background in AI to quantum machine learning (QML)—a rapidly evolving field that seeks to leverage the power of quantum computers to reshape the landscape of machine learning. For self-consistency, this tutorial covers foundational principles, representative QML algorithms, their potential applications, and critical aspects such as trainability, generalization, and computational complexity. In addition, practical code demonstrations are provided in https://***/ to illustrate real-world implementations and facilitate hands-on learning. Together, these elements offer readers a comprehensive overview of the latest advancements in QML. By bridging the gap between classical machine learning and quantum computing, this tutorial serves as a valuable resource for those looking to engage with QML and explore the forefront of AI in the quantum era. © 2025, CC BY.

关键词： Adversarial machine learning

Hybrid Machine Learning Approach: SVM with ANN Kernel for HSI Medical Image Enhancement 2

学校读者我要写书评

暂无评论

Hybrid Machine Learning Approach: SVM with ANN Kernel for HS...

2nd IEEE International Conference on Emerging Research in Computational science, ICERCS 2024

作者： Aravindhan, K. Revathi, K. Priyanka, S. Priyadharshini, S. Keerthana, P.K. Muthulakshmi, K. REVA University School of Computing and Information Technology Karnataka Bengaluru India SNS College of Engineering Department of Information Technology Tamil Nadu Coimbatore India SNS College of Engineering Department of Artificial Intelligence and Data Science Tamilnadu Coimbatore India KGiSL Institute of Technology Department of Electronics and Communication Engineering Tamil Nadu Coimbatore India Manipal Institute of Technology Department of Information Technology Karnataka Bengaluru India

ISBN: (纸本)9798331534950

In medicine image processing provides a perceptive study on disease diagnosis and identification as well as treatment preparation. Since it can acquire complete spectral information over a wide spectrum of wavelengths, especially hyperspectral imaging (HSI) has shown great potential for the non-invasive characterization of tissue. On the other hand, due to their high-dimensional character as well as the presence of noise HSI medical images present a great challenge for processing and enhancement. Even if traditional methods are effective since they sometimes struggle to manage the complexity of these datasets, more sophisticated approaches are needed and demanded. The proposed a hybrid machine learning model including a support vector machine (SVM) classifier and an artificial neural network (ANN) kernel inside the scope of this work to improve and classify HSI images. The ANN kernel is designed to control the inherently complex and non-linear elements in HSI data. Acting as a mapping tool, the artificial neural network kernel transforms the input space into a feature space easily managed in which the SVM can operate with higher accuracy. Main goals are to lower image noise and increase contrast to improve diagnosis correctness. The method was evaluated with a readily available general public HSI medical image collection. In the experimental results, image quality and classification accuracy show appreciable rise. Comparatively to the traditional SVM methods, the signal-to-noise ratio (SNR) increased by 15%;hence, the general classification accuracy was found to be 94.8%. Moreover, the better images show more clear tissue limits and spectral features, which helps clinical interpretation of the results. The results imply that the SVM with ANN kernel model provides a strong solution for the enhancement and classification of HSI medical images, so opening a new path for the improvement of medical diagnostics. © 2024 IEEE.

关键词： Support vector machines

Accurate Generated Text Detection Based on Deep Layer-wise Relevance Propagation

学校读者我要写书评

暂无评论

Accurate Generated Text Detection Based on Deep Layer-wise R...

IEEE International Conference on Big data Analysis (ICBDA)

作者： Mengjie Guo Limin Liu Meicheng Guo Siyuan Liu Zhiwei Xu Chinese Academy of Sciences Institute of Computing Technology Beijing China College of Data Science and Application Inner Mongolia University of Technology Hohhot China

Text generation models (TGMs) excel in producing text that matches the style of human language reasonably well. Such TGMs (e.g., GAN-based text generation model) can be misused for fake news and fake product reviews that can look authentic and fool humans. To distinguish the generated texts by TGM from the real texts, the latest detection models leverage learning algorithms with a variety of features to improve the detection performance against generated texts. However, the features included in these models are usually not relevant to the deep semantic correlation and fail to achieve accurate detection of the generated texts. To handle this problem, we propose a deep interpretable model to achieve accurate detection of the generated texts. In detail, a feature extraction method based on Layer-wise Relevance Propagation is proposed to improve the feature mining performance for detection of generated texts. Experiments based on real-world datasets demonstrate that the proposed model achieves more accurate generated text detection and significantly outperforms state-of-the-art detection schemes.

关键词： Analytical models Correlation Semantics Big data Feature extraction data models Fake news

Thematic Event Extraction Based on Event-Related Sentence Detection

学校读者我要写书评

暂无评论

Thematic Event Extraction Based on Event-Related Sentence De...

Medical Artificial Intelligence (MedAI), IEEE International Conference on

作者： Xing Zhang Yucan Guo Xiaolong Jin Haozhe Liang Saiping Guan School of Computer Science and Technology University of Chinese Academy of Sciences CAS Key Laboratory of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences Institute of Systems Engineering Academy of Military Science

Existing works in event extraction typically extract event arguments within the sentence scope. However, besides the sentence level, events may also be naturally presented at the document level. A document-level event usually reflects, to some extent, the theme (i.e., the main content) of the document (e.g., electronic medical records and news articles), which is thus referred to as the thematic event. Thematic Event Extraction (TEE) aims to extract the arguments of thematic events. TEE faces a major challenge, i.e., the sparsity and dispersion of arguments, which means that the arguments of a thematic event are dispersed in different sentences of the document. To overcome this challenge, we propose an Event-related Sentence Detection based TEE model, called ESDTEE, which first detects the sentences related to the thematic event and then extracts the arguments only within these detected sentences using existing models. Extensive experiments with comprehensive analyses demonstrate the effectiveness of ESDTEE.

关键词：

Performance and Security Evaluation of Chaotic Maps for Image Scrambling in Real-Time Applications

学校读者我要写书评

暂无评论

Performance and Security Evaluation of Chaotic Maps for Imag...

3rd IEEE International Conference on Interdisciplinary Approaches in Technology and Management for Social Innovation, IATMSI 2025

作者： Subashini, B. Panjatcharam, V.G. Saradha, S. Srm Institute of Science and Technology School of Computing College of Engineering and Technology Dept of Data Science and Business Systems Chennai India Vet Institute of Arts & Science(Co-Ed) College Dept of Mca Thindal Erode India Nandha Engineering College (Autonomous) Dept of Mca Erode India

ISBN: (数字)9798331521691

ISBN: (纸本)9798331521707

Image scrambling is an essential technique in secure image transmission, designed to obscure visual data from unauthorized access while preserving the ability to recover the original content. This study investigates the application of five chaotic maps such as Logistic Map, Arnold Cat Map, Lorenz System, Henon Map and Tent Map for image scrambling. Performance is evaluated using key metrics: Normalized Cross-Correlation (NCC), entropy, Peak Signal-to-Noise Ratio (PSNR), Structural Similarity Index (SSIM) and time complexity. Results indicate that the Arnold Cat Map provides the highest entropy (5.8680) and strong decorrelation (NCC = 0.8715), making it ideal for high-security applications. The Logistic Map, with the fastest execution time (0.0039 seconds), is suitable for real-time applications, offering moderate security and good image quality (PSNR = 11.5170, SSIM = 0.0229). The Lorenz System exhibited the best decorrelation (NCC = 0.8657), but its high computational cost limits its use in time-sensitive environments. By comparing the PSNR and SSIM results, this study highlights the balance between visual quality and security, suggesting that chaotic maps can be tailored for specific s ecurity n eeds. The novelty lies in the systematic comparison of these chaotic maps, providing a comprehensive evaluation for optimizing security and performance. © 2025 IEEE.

关键词： Arnold Cat Map Henon Map Image Scrambling Logistic Map Lorenz System Tent Map