检索结果-内蒙古大学图书馆

Unifying (Machine) Vision via Counterfactual World Modeling

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Bear, Daniel M. Feigelis, Kevin Chen, Honglin Lee, Wanhee Venkatesh, Rahul Kotar, Klemen Durango, Alex Yamins, Daniel L.K. Department of Psychology Stanford University StanfordCA94305 United States Department of Physics Stanford University StanfordCA94305 United States Department of Computer Science Stanford University StanfordCA94305 United States Department of Applied Physics Stanford University StanfordCA94305 United States Neurosciences Graduate Program Stanford University StanfordCA94305 United States Wu Tsai Neurosciences Institute Stanford University StanfordCA94305 United States

Leading approaches in machine vision employ different architectures for different tasks, trained on costly task-specific labeled datasets. This complexity has held back progress in areas, such as robotics, where robust task-general perception remains a bottleneck. In contrast, "foundation models" of natural language have shown how large pre-trained neural networks can provide zero-shot solutions to a broad spectrum of apparently distinct tasks. Here we introduce Counterfactual World Modeling (CWM), a framework for constructing a visual foundation model: a unified, unsupervised network that can be prompted to perform a wide variety of visual computations. CWM has two key components, which resolve the core issues that have hindered application of the foundation model concept to vision. The first is structured masking, a generalization of masked prediction methods that encourages a prediction model to capture the low-dimensional structure in visual data. The model thereby factors the key physical components of a scene and exposes an interface to them via small sets of visual tokens. This in turn enables CWM’s second main idea – counterfactual prompting – the observation that many apparently distinct visual representations can be computed, in a zero-shot manner, by comparing the prediction model’s output on real inputs versus slightly modified ("counterfactual") inputs. We show that CWM generates high-quality readouts on real-world images and videos for a diversity of tasks, including estimation of keypoints, optical flow, occlusions, object segments, and relative depth. Taken together, our results show that CWM is a promising path to unifying the manifold strands of machine vision in a conceptually simple foundation. © 2023, CC BY.

关键词： computer vision

Minimizing Quantum Rényi Divergences via Mirror Descent with Polyak Step Size

学校读者我要写书评

暂无评论

arXiv 2021年

作者： You, Jun-Kai Cheng, Hao-Chung Li, Yen-Huan Department of Computer Science and Information Engineering National Taiwan University Taiwan Department of Mathematics National Taiwan University Taiwan Department of Electrical Engineering Graduate Institute of Communication Engineering National Taiwan University Taiwan Quantum Computing Centre Center for Quantum Science and Engineering National Taiwan University Taiwan

Quantum information quantities play a substantial role in characterizing operational quantities in various quantum information-theoretic problems. We consider the numerical computation of four quantum information quantities: Petz-Augustin information, sandwiched Augustin information, conditional sandwiched Rényi entropy, and sandwiched Rényi information. To compute these quantities requires minimizing some order-α quantum Rényi divergences over the set of quantum states. Whereas the optimization problems are obviously convex, they violate standard bounded gradient/Hessian conditions in literature, so existing convex optimization methods and their convergence guarantees do not directly apply. In this paper, we propose a new class of convex optimization methods called mirror descent with the Polyak step size. We prove their convergence under a weak condition, showing that they provably converge for minimizing quantum Rényi divergences. Numerical experiment results show that entropic mirror descent with the Polyak step size converges fast in minimizing quantum Rényi divergences. Copyright © 2021, The Authors. All rights reserved.

关键词： Quantum optics

Drum-aware ensemble architecture for improved joint musical beat and downbeat tracking

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Chiu, Ching-Yu Su, Alvin Wen-Yu Yang, Yi-Hsuan The Graduate Program of Multimedia Systems and Intelligent Computing National Cheng Kung University Academia Sinica Taiwan The Department of Computer Science and Information Engineering National Cheng Kung University Taiwan Yating Music Team Taiwan AI Labs Taiwan Research Center for IT Innovation Academia Sinica Taiwan

This paper presents a novel system architecture that integrates blind source separation with joint beat and downbeat tracking in musical audio signals. The source separation module segregates the percussive and non-percussive components of the input signal, over which beat and downbeat tracking are performed separately and then the results are aggregated with a learnable fusion mechanism. This way, the system can adaptively determine how much the tracking result for an input signal should depend on the input's percussive or non-percussive components. Evaluation on four testing sets that feature different levels of presence of drum sounds shows that the new architecture consistently outperforms the widely-adopted baseline architecture that does not employ source separation. Copyright © 2021, The Authors. All rights reserved.

关键词： Blind source separation

Enhancing Deep Reinforcement Learning: A Tutorial on Generative Diffusion Models in Network Optimization

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Du, Hongyang Zhang, Ruichen Liu, Yinqiu Wang, Jiacheng Lin, Yijing Li, Zonghang Niyato, Dusit Kang, Jiawen Xiong, Zehui Cui, Shuguang Ai, Bo Zhou, Haibo Kim, Dong In The School of Computer Science and Engineering The Energy Research Institute @ NTU Interdisciplinary Graduate Program Nanyang Technological University Singapore The School of Computer Science and Engineering Nanyang Technological University Singapore The State Key Laboratory of Networking and Switching Technology Beijing University of Posts and Telecommunications China The School of Information and Communication Engineering University of Electronic Sciences and Technology of China Chengdu China The School of Automation Guangdong University of Technology China The Pillar of Information Systems Technology and Design Singapore University of Technology and Design Singapore Shenzhen China The State Key Laboratory of Rail Traffic Control and Safety Beijing Jiaotong University Beijing100044 China School of Electronic Science and Engineering Nanjing University Jiangsu Nanjing210093 China The Department of Electrical and Computer Engineering Sungkyunkwan University Suwon16419 Korea Republic of

Generative Diffusion Models (GDMs) have emerged as a transformative force in the realm of Generative Artificial Intelligence (GenAI), demonstrating their versatility and efficacy across various applications. The ability to model complex data distributions and generate high-quality samples has made GDMs particularly effective in tasks such as image generation and reinforcement learning. Furthermore, their iterative nature, which involves a series of noise addition and denoising steps, is a powerful and unique approach to learning and generating data. This paper serves as a comprehensive tutorial on applying GDMs in network optimization tasks. We delve into the strengths of GDMs, emphasizing their wide applicability across various domains, such as vision, text, and audio generation. We detail how GDMs can be effectively harnessed to solve complex optimization problems inherent in networks. The paper first provides a basic background of GDMs and their applications in network optimization. This is followed by a series of case studies, showcasing the integration of GDMs with Deep Reinforcement Learning (DRL), incentive mechanism design, Semantic Communications (SemCom), Internet of Vehicles (IoV) networks, etc. These case studies underscore the practicality and efficacy of GDMs in real-world scenarios, offering insights into network design. We conclude with a discussion on potential future directions for GDM research and applications, providing major insights into how they can continue to shape the future of network optimization. © 2023, CC BY.

关键词： Reinforcement learning

Transfer learning approach to modeling multichannel gate-all-around nanosheet field-effect transistors under work function fluctuations

学校读者我要写书评

暂无评论

Engineering Applications of Artificial Intelligence 2025年 148卷

作者： Dash, Sagarika Li, Yiming Parallel and Scientific Computing Laboratory National Yang-Ming Chiao Tung University 1001 Ta-Hsueh Rd. Hsinchu300093 Taiwan Electrical Engineering and Computer Science International Graduate Program National Yang-Ming Chiao Tung University 1001 Ta-Hsueh Rd. Hsinchu300093 Taiwan Institute of Communications Engineering National Yang-Ming Chiao Tung University 1001 Ta-Hsueh Rd. Hsinchu300093 Taiwan Institute of Biomedical Engineering National Yang-Ming Chiao Tung University 1001 Ta-Hsueh Rd. Hsinchu300093 Taiwan Institute of Pioneer Semiconductor Innovation National Yang-Ming Chiao Tung University 1001 Ta-Hsueh Rd. Hsinchu300093 Taiwan Institute of Artificial Intelligence Innovation National Yang-Ming Chiao Tung University 1001 Ta-Hsueh Rd. Hsinchu300093 Taiwan Department of Electronics and Electrical Engineering National Yang-Ming Chiao Tung University 1001 Ta-Hsueh Rd. Hsinchu300093 Taiwan Department of Microelectronics National Yang-Ming Chiao Tung University 1001 Ta-Hsueh Rd. Hsinchu300093 Taiwan

Deep learning (DL) has significantly advanced various industries, including semiconductors, by providing sophisticated methods for analyzing emerging device data. Transfer learning (TL), a prominent DL topology, leverages knowledge from a pre-trained model to improve the performance of a specific target task. This study aims to apply TL to predict the impact of work function fluctuation (WKF) on the variability of threshold voltage (σVTH) in gate-all-around silicon nanosheet field-effect transistors (GAA Si NS FETs). We used TL to transfer knowledge from models trained on 1-channel (1ch) GAA Si NS FETs to more complex 4-channel (4ch) counterparts. The prediction accuracy is evaluated by using the mean square error(MSE), root mean square error (RMSE), and the mean absolute error(MAE) metrics. Our TL approach achieved an error rate of less than 1%, demonstrating high accuracy in predicting WKF effects on σ VTH of 4ch GAA Si NS FETs using only 500 samples. This study presents a pioneering application of TL using a one-dimensional (1D) convolutional neural network (CNN) long short-term memory (LSTM) topology in semiconductor device technology. The results effectively address the challenge of predicting σ VTH variations in advanced GAA Si NS FETs because of WKF, which eliminates the need for extensive semiconductor device simulations. © 2025 Elsevier Ltd

关键词： Convolutional neural networks

Reactive supervision: A new method for collecting sarcasm data

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Shmueli, Boaz Ku, Lun-Wei Ray, Soumya Social Networks and Human-Centered Computing Taiwan International Graduate Program Taiwan Institute of Information Science Academia Sinica Taiwan Institute of Service Science National Tsing Hua University Taiwan

Sarcasm detection is an important task in affective computing, requiring large amounts of labeled data. We introduce reactive supervision, a novel data collection method that utilizes the dynamics of online conversations to overcome the limitations of existing data collection techniques. We use the new method to create and release a first-of-its-kind large dataset of tweets with sarcasm perspective labels and new contextual features. The dataset is expected to advance sarcasm detection research. Our method can be adapted to other affective computing domains, thus opening up new research opportunities. Copyright © 2020, The Authors. All rights reserved.

关键词： Large dataset

Gene knockout inference with variational graph autoencoder learning single-cell gene regulatory networks

学校读者我要写书评

暂无评论

Nucleic acids research 2023年第13期51卷 6578-6592页

作者： Yongjian Yang Guanxun Li Yan Zhong Qian Xu Bo-Jia Chen Yu-Te Lin Robert S Chapkin James J Cai Department of Electrical and Computer Engineering Texas A&M University College Station TX 77843 USA. Department of Statistics Texas A&M University College Station TX 77843 USA. Key Laboratory of Advanced Theory and Application in Statistics and Data Science-MOE School of Statistics East China Normal University 3663 North Zhongshan Road Shanghai 200062 China. Department of Veterinary Integrative Biosciences Texas A&M University College Station TX 77843 USA. Graduate Institute of Microbiology and Public Health College of Veterinary Medicine National Chung Hsing University Taichung 402 Taiwan. Graduate Institute of Biomedical Electronics and Bioinformatics National Taiwan University Taipei Taiwan. Program in Integrative & Complex Diseases Department of Nutrition Texas A&M University College Station TX 77843 USA. Interdisciplinary Program of Genetics Texas A&M University College Station TX 77843 USA.

In this paper, we introduce Gene Knockout Inference (GenKI), a virtual knockout (KO) tool for gene function prediction using single-cell RNA sequencing (scRNA-seq) data in the absence of KO samples when only wild-type (WT) samples are available. Without using any information from real KO samples, GenKI is designed to capture shifting patterns in gene regulation caused by the KO perturbation in an unsupervised manner and provide a robust and scalable framework for gene function studies. To achieve this goal, GenKI adapts a variational graph autoencoder (VGAE) model to learn latent representations of genes and interactions between genes from the input WT scRNA-seq data and a derived single-cell gene regulatory network (scGRN). The virtual KO data is then generated by computationally removing all edges of the KO gene-the gene to be knocked out for functional study-from the scGRN. The differences between WT and virtual KO data are discerned by using their corresponding latent parameters derived from the trained VGAE model. Our simulations show that GenKI accurately approximates the perturbation profiles upon gene KO and outperforms the state-of-the-art under a series of evaluation conditions. Using publicly available scRNA-seq data sets, we demonstrate that GenKI recapitulates discoveries of real-animal KO experiments and accurately predicts cell type-specific functions of KO genes. Thus, GenKI provides an in-silico alternative to KO experiments that may partially replace the need for genetically modified animals or other genetically perturbed systems.

关键词：

Faster Gröbner bases for Lie derivatives of ODE systems via monomial orderings

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Bessonov, Mariya Ilmer, Ilia Konstantinova, Tatiana Ovchinnikov, Alexey Pogudin, Gleb Soto, Pedro Department of Mathematics CUNY NYC College of Technology New YorkNY United States Ph.D. Program in Computer Science CUNY Graduate Center New YorkNY United States Department of Mathematics CUNY Queens College New YorkNY United States LIX CNRS École Polytechnique Institute Polytechnique de Paris Paris France

Symbolic computation for systems of differential equations is often computationally expensive. Many practical differential models have a form of polynomial or rational ODE system with specified outputs. A basic symbolic approach to analyze these models is to compute and then symbolically process the polynomial system obtained by sufficiently many Lie derivatives of the output functions with respect to the vector field given by the ODE system. In this paper, we present a method for speeding up Gröbner basis computation for such a class of polynomial systems by using specific monomial ordering, including weights for the variables, coming from the structure of the ODE model. We provide empirical results that show improvement across different symbolic computing frameworks and apply the method to speed up structural identifiability analysis of ODE models. © 2022, CC BY-NC-SA.

关键词： Polynomials

Observation of Colossal Terahertz Magnetoresistance and Magnetocapacitance in a Perovskite Manganite

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Tay, Fuyang Chaudhary, Swati He, Jiaming Peraca, Nicolas Marquez Baydin, Andrey Fiete, Gregory A. Zhou, Jianshi Kono, Junichiro Department of Electrical and Computer Engineering Rice University HoustonTX77005 United States Applied Physics Graduate Program Smalley-Curl Institute Rice University HoustonTX77005 United States Department of Physics University of Texas at Austin AustinTX78712 United States Department of Physics Northeastern University BostonMA02115 United States Department of Physics Massachusetts Institute of Technology CambridgeMA02139 United States Materials Science and Engineering Program Mechanical Engineering University of Texas at Austin AustinTX78712 United States Department of Physics and Astronomy Rice University HoustonTX77005 United States Smalley-Curl Institute Rice University HoustonTX77005 United States Department of Materials Science and NanoEngineering Rice University HoustonTX77005 United States

We have studied the terahertz response of a bulk single crystal of La0.875Sr0.125MnO3at around its Curie temperature, observing large changes in the real and imaginary parts of the optical conductivity as a function of magnetic field. The terahertz resistance and capacitance extracted from the optical conductivity rapidly increased with increasing magnetic field and did not show any sign of saturation up to 6 T, reaching 60% and 15%, respectively, at 180 K. The observed terahertz colossal magnetoresistance and magnetocapacitance effects can be qualitatively explained by using a two-component model that assumes the coexistence of two phases with vastly different conductivities. These results demonstrate the potential use of perovskite manganites for developing efficient terahertz devices based on magnetic modulations of the amplitude and phase of terahertz waves. Copyright © 2023, The Authors. All rights reserved.

关键词： Optical conductivity