检索结果-内蒙古大学图书馆

Position: Topological Deep Learning is the New Frontier for Relational Learning 41

学校读者我要写书评

暂无评论

Position: Topological Deep Learning is the New Frontier for ...

41st International Conference on Machine Learning, ICML 2024

作者： Papamarkou, Theodore Birdal, Tolga Bronstein, Michael Carlsson, Gunnar Curry, Justin Gao, Yue Hajij, Mustafa Kwitt, Roland Liò, Pietro Di Lorenzo, Paolo Maroulas, Vasileios Miolane, Nina Nasrin, Farzana Ramamurthy, Karthikeyan Natesan Rieck, Bastian Scardapane, Simone Schaub, Michael T. Veličković, Petar Wang, Bei Wang, Yusu Wei, Guo-Wei Zamzmi, Ghada Department of Mathematics The University of Manchester Manchester United Kingdom Department of Computing Imperial College London London United Kingdom Department of Computer Science University of Oxford Oxford United Kingdom Department of Mathematics Stanford University Stanford United States BlueLightAI Inc. United States University at Albany New York United States School of Software Tsinghua University Beijing China University of San Francisco San Francisco United States Department of Artificial Intelligence and Human Interfaces University of Salzburg Austria Department of Computer Science and Technology University of Cambridge Cambridge United Kingdom Department of Information Engineering Electronics and Telecommunications Sapienza University of Rome Rome Italy Department of Mathematics University of Tennessee Knoxville United States Department of Electrical and Computer Engineering UC Santa Barbara Santa Barbara United States Department of Mathematics University of Hawai'i at Mānoa HI United States IBM Corporation New York United States Helmholtz Munich Munich Germany Technical University of Munich Munich Germany RWTH Aachen University Aachen Germany Google Deep-Mind United Kingdom School of Computing University of Utah Utah United States Computer Science and Engineering Department University of California San Diego San Diego United States Department of Mathematics Michigan State University East LansingMI United States University of South Florida Florida United States

Topological deep learning (TDL) is a rapidly evolving field that uses topological features to understand and design deep learning models. This paper posits that TDL is the new frontier for relational learning. TDL may complement graph representation learning and geometric deep learning by incorporating topological concepts, and can thus provide a natural choice for various machine learning settings. To this end, this paper discusses open problems in TDL, ranging from practical benefits to theoretical foundations. For each problem, it outlines potential solutions and future research opportunities. At the same time, this paper serves as an invitation to the scientific community to actively participate in TDL research to unlock the potential of this emerging field. Copyright 2024 by the author(s)

关键词： Adversarial machine learning

Knowledge-Grounded Self-Rationalization via Extractive and Natural Language Explanations

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Majumder, Bodhisattwa Prasad Camburu, Oana-Maria Lukasiewicz, Thomas McAuley, Julian Department of Computer Science and Engineering UC San Diego United States Department of Computer Science University of Oxford United Kingdom Institute of Logic and Computation TU Wien Austria

Models that generate extractive rationales (i.e., subsets of features) or natural language explanations (NLEs) for their predictions are important for explainable AI. While an extractive rationale provides a quick view of the features most responsible for a prediction, an NLE allows for a comprehensive description of the decision-making process behind a prediction. However, current models that generate the best extractive rationales or NLEs often fall behind the state-of-the-art (SOTA) in terms of task performance. In this work, we bridge this gap by introducing REXC, a self-rationalizing framework that grounds its predictions and two complementary types of explanations (NLEs and extractive rationales) in background knowledge. Our framework improves over previous methods by: (i) reaching SOTA task performance while also providing explanations, (ii) providing two types of explanations, while existing models usually provide only one type, and (iii) beating by a large margin the previous SOTA in terms of quality of both types of explanations. Furthermore, a perturbation analysis in REXC shows a high degree of association between explanations and predictions, a necessary property of faithful explanations. © 2021, CC BY.

关键词： Forecasting

FogROS2: An Adaptive Platform for Cloud and Fog Robotics Using ROS 2

学校读者我要写书评

暂无评论

FogROS2: An Adaptive Platform for Cloud and Fog Robotics Usi...

IEEE International Conference on Robotics and Automation (ICRA)

作者： Jeffrey Ichnowski Kaiyuan Chen Karthik Dharmarajan Simeon Adebola Michael Danielczuk Víctor Mayoral-Vilches Nikhil Jha Hugo Zhan Edith Llontop Derek Xu Camilo Buscaron John Kubiatowicz Ion Stoica Joseph Gonzalez Ken Goldberg Department of Electrical Engineering and Computer Science University of California Berkeley CA USA Robotics Institute Carnegie Mellon University The AUTOLab UC Berkeley Acceleration Robotics Vitoria Álava Spain System Security Group Universität Klagenfurt Klagenfurt Austria Department of Industrial Engineering and Operations Research University of California Berkeley CA USA

Mobility, power, and price points often dictate that robots do not have sufficient computing power on board to run contemporary robot algorithms at desired rates. Cloud computing providers such as AWS, GCP, and Azure offer immense computing power and increasingly low latency on demand, but tapping into that power from a robot is non-trivial. We present FogROS2, an open-source platform to facilitate cloud and fog robotics that is included in the Robot Operating System 2 (ROS 2) distribution. FogROS2 is distinct from its predecessor FogROS1 in 9 ways, including lower latency, overhead, and startup times; improved usability, and additional automation, such as region and computer type selection. Additionally, FogROS2 gains performance, timing, and additional improvements associated with ROS 2. In common robot applications, FogROS2 reduces SLAM latency by 50 %, reduces grasp planning time from 14 s to 1.2 s, and speeds up motion planning 45x. When compared to FogROS1, FogROS2 reduces network utilization by up to 3.8x, improves startup time by 63 %, and network round-trip latency by 97 % for images using video compression. The source code, examples, and documentation for FogROS2 are available at https://***/BerkeleyAutomation/FogROS2, and is available through the official ROS 2 repository at https://***/p/FogROS2/.

关键词：

Structural inversion asymmetry in epitaxial ultrathin films of Bi(111)/InSb(111)B

学校读者我要写书评

暂无评论

Physical Review Materials 2025年第5期9卷 054202-054202页

作者： Hadass S. Inbar Muhammad Zubair Jason T. Dong Aaron N. Engel Connor P. Dempsey Yu Hao Chang Shinichi Nishihaya Shoaib Khalid Alexei V. Fedorov Anderson Janotti Chris J. Palmstrøm Materials Department UC Santa Barbara California 93106 USA Department of Physics and Astronomy University of Delaware Newark Delaware 19716 USA Department of Materials Science and Engineering University of Delaware Newark Delaware 19716 USA Department of Electrical & Computer Engineering UC Santa Barbara California 93106 USA Present address: Department of Physics Tokyo Institute of Technology Tokyo 152-8551 Japan. Princeton Plasma Physics Laboratory Princeton New Jersey 08540 USA Advanced Light Source Lawrence Berkeley National Laboratory Berkeley California 94720 USA

Bismuth (Bi) films hold potential for spintronic devices due to strong spin-orbit coupling. Understanding the growth, surface states, and interactions with the substrate is key to their functionalization. Large-area high-quality (111) Bi ultrathin films were grown on InSb (111)B substrates by molecular beam epitaxy (MBE). Strong film-substrate interactions epitaxially stabilize the (111) orientation and lead to nonequivalent interface potentials. Analysis of angle-resolved photoemission spectroscopy (ARPES) measurements, employed to characterize the evolution of the surface states with film thickness, indicate a crossing at the M¯ point, suggesting a topologically trivial phase in the thin film. The results show the presence of interfacial bonds to the substrate breaks inversion symmetry, preventing the semimetal-to-semiconductor transition predicted for freestanding bismuth layers, highlighting the importance of controlled functionalization and surface passivation of two-dimensional materials.

关键词： Ultrathin films

High-fidelity Direct Contrast Synthesis from Magnetic Resonance Fingerprinting

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Wang, Ke Doneva, Mariya Meineke, Jakob Amthor, Thomas Karasan, Ekin Tan, Fei Tamir, Jonathan I. Yu, Stella X. Lustig, Michael Electrical Engineering and Computer Sciences University of California Berkeley BerkeleyCA United States Philips Research Europe Hamburg Germany Bioengineering UC Berkeley-UCSF San FranciscoCA United States Chandra Family Department of Electrical and Computer Engineering The University of Texas at Austin AustinTX United States International Computer Science Institute BerkeleyCA United States Computer Science and Engineering University of Michigan Ann ArborMI United States

Magnetic Resonance Fingerprinting (MRF) is an efficient quantitative MRI technique that can extract important tissue and system parameters such as T1, T2, B0, and B1 from a single scan. This property also makes it attractive for retrospectively synthesizing contrast-weighted images. In general, contrast-weighted images like T1-weighted, T2-weighted, etc. can be synthesized directly from parameter maps through spin-dynamics simulation (i.e., Bloch or Extended Phase Graph models). However, these approaches often exhibit artifacts due to imperfections in the mapping, the sequence modeling, and the data acquisition. Here we propose a supervised learning-based method that directly synthesizes contrast-weighted images from the MRF data without going through the quantitative mapping and spin-dynamics simulation. To implement our direct contrast synthesis (DCS) method, we deploy a conditional Generative Adversarial Network (GAN) framework and propose a multi-branch U-Net as the generator. The input MRF data are used to directly synthesize T1-weighted, T2-weighted, and fluid-attenuated inversion recovery (FLAIR) images through supervised training on paired MRF and target spin echo-based contrast-weighted scans. In-vivo experiments demonstrate excellent image quality compared to simulation-based contrast synthesis and previous DCS methods, both visually as well as by quantitative metrics. We also demonstrate cases where our trained model is able to mitigate in-flow and spiral off-resonance artifacts that are typically seen in MRF reconstructions and thus more faithfully represent conventional spin echo-based contrast-weighted images. © 2022, CC0.

关键词： Generative adversarial networks

Highway: Efficient consensus with flexible finality

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Kane, Daniel Fackler, Andreas Gągol, Adam Straszak, Damian Computer Science and Engineering Department UC San Diego United States CasperLabs AG Switzerland Cardinal Cryptography Germany

There has been recently a lot of progress in designing efficient partially synchronous BFT consensus protocols that are meant to serve as core consensus engines for Proof of Stake blockchain systems. While the state-of-the-art solutions attain virtually optimal performance under this theoretical model, there is still room for improvement, as several practical aspects of such systems are not captured by this model. Most notably, during regular execution, due to financial incentives in such systems, one expects an overwhelming fraction of nodes to honestly follow the protocol rules and only few of them to be faulty, most likely due to temporary network issues. Intuitively, the fact that almost all nodes behave honestly should result in stronger confidence in blocks finalized in such periods, however it is not the case under the classical model, where finality is binary. We propose Highway, a new consensus protocol that is safe and live in the classical partially synchronous BFT model, while at the same time offering practical improvements over existing solutions. Specifically, block finality in Highway is not binary but is expressed by fraction of nodes that would need to break the protocol rules in order for a block to be reverted. During periods of honest participation finality of blocks might reach well beyond 1∕3 (as what would be the maximum for classical protocols), up to even 1 (complete certainty). Having finality defined this way, Highway offers flexibility with respect to the configuration of security thresholds among nodes running the protocol, allowing nodes with lower thresholds to reach finality faster than the ones requiring higher levels of confidence. Copyright © 2021, The Authors. All rights reserved.

关键词： Machine learning

RF Backscatter-Based Sensors for Structural Health Monitoring 4

学校读者我要写书评

暂无评论

RF Backscatter-Based Sensors for Structural Health Monitorin...

4th International Balkan Conference on Communications and Networking, BalkanCom 2021

作者： Stanacevic, Milutin Ahmad, Abeer Sha, Xiao Athalye, Akshay Das, Samir Caylor, Kelly Glisic, Branko Djuric, Petar M. Stony Brook University Department of Electrical and Computer Engineering Stony BrookNY11794 United States Stony Brook University Department of Computer Science Stony BrookNY11794 United States UC Santa Barbara Department of Geography Santa BarbaraCA93106 United States Princeton University Civil and Environmental Engineering PrincetonNJ08544 United States

ISBN: (纸本)9781665402583

There is a growing need for accurate and reliable assessment of conditions of a variety of engineering structures and for monitoring of their performance. Miniaturized, passive, backscatter-based RF sensors with embedded computational capabilities could enable advanced structural health monitoring at high fidelity and at large-scale. Specifically, these RF-powered devices, pervasively embedded and dispersed within the structural material, can sense parameters of interest throughout large volumes of instrumented structure, perform modest local computations to infer structural conditions, and communicate via backscatter modulation while consuming near-zero power. We demonstrate that the backscatter channel phase sensing enables quantification of a size of air gap between two RF sensors embedded in sand. Additionally, we demonstrate the sensitivity of the phase to the strain of the sand. © 2021 IEEE.

关键词： Structural health monitoring

Tunable Source of Quantum-Correlated Photons with Integrated Pump Rejection in a Silicon CMOS Platform

学校读者我要写书评

暂无评论

Tunable Source of Quantum-Correlated Photons with Integrated...

Frontiers in Optics + Laser science 2021, FiO+LS 2021 - Part of Frontiers in Optics, FiO 2021

作者： Fargas Cabanillas, Josep M. Kramnik, Danielius Ramesh, Anirudh Gentry, Cale M. Stojanović, Vladimir Kumar, Prem Popović, Miloš A. Department of Electrical and Computer Engineering Photonics Center Boston University BostonMA02215 United States Department of Electrical Engineering and Computer Science UC Berkeley BerkeleyCA94720 United States Graduate Program in Applied Physics Northwestern University EvanstonIL60208 United States Department of Electrical Computer and Energy Engineering University of Colorado BoulderCO80309 United States Center for Photonic Communication and Computing Dept. of Electrical and Computer Eng. Northwestern University EvanstonIL60208 United States

ISBN: (纸本)9781557528209

A wavelength-tunable, silicon photon-pair source based on spontaneous four-wave mixing, integrated with a pump rejection filter in a single, flip-chip packaged CMOS chip, is demonstrated with a coincidence-to-accidentals ratio of 9.1 with no off-chip pump filtering. Frontiers in Optics / Laser science © Optica Publishing Group 2021.

关键词： CMOS integrated circuits

Type Information Utilized Event Detection via Multi-Channel GNNs in Electrical Power Systems

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Li, Qian Li, Jianxin Wang, Lihong Ji, Cheng Hei, Yiming Sheng, Jiawei Sun, Qingyun Xue, Shan Xie, Pengtao School of Computer Science and Engineering Beihang University Haidian Beijing China National Computer Network Emergency Response Technical Team Coordination Center of China Beijing China School of Cyber Science and Technology Beihang University Haidian Beijing China Institute of Information Engineering Chinese Academy of Sciences Beijing China School of Computing Macquarie University Sydney Australia Department of Electrical and Computer Engineering UC San Diego United States

Event detection in power systems aims to identify triggers and event types, which helps relevant personnel respond to emergencies promptly and facilitates the optimization of power supply strategies. However, the limited length of short electrical record texts causes severe information sparsity, and numerous domain-specific terminologies of power systems makes it difficult to transfer knowledge from language models pre-trained on general-domain texts. Traditional event detection approaches primarily focus on the general domain and ignore these two problems in the power system domain. To address the above issues, we propose a Multi-Channel graph neural network utilizing Type information for Event Detection in power systems, named MC-TED, leveraging a semantic channel and a topological channel to enrich information interaction from short texts. Concretely, the semantic channel refines textual representations with semantic similarity, building the semantic information interaction among potential event-related words. The topological channel generates a relation-type-aware graph modeling word dependencies, and a word-type-aware graph integrating part-of-speech tags. To further reduce errors worsened by professional terminologies in type analysis, a type learning mechanism is designed for updating the representations of both the word type and relation type in the topological channel. In this way, the information sparsity and professional term occurrence problems can be alleviated by enabling interaction between topological and semantic information. Furthermore, to address the lack of labeled data in power systems, we built a Chinese event detection dataset based on electrical Power Copyright © 2022, The Authors. All rights reserved.

关键词： Semantics