检索结果-内蒙古大学图书馆

Conceptualizing Machine Learning for Dynamic Information Retrieval of Electronic Health Record Notes

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Jiang, Sharon Shen, Shannon Agrawal, Monica Lam, Barbara Kurtzman, Nicholas Horng, Steven Karger, David Sontag, David Department of Electrical Engineering & Computer Science MIT CambridgeMA United States Division of Hematology & Oncology Department of Medicine Beth Israel Deaconess Medical Center BostonMA United States Division of Clinical Informatics Department of Medicine Beth Israel Deaconess Medical Center BostonMA United States Department of Emergency Medicine Beth Israel Deaconess Medical Center BostonMA United States

The large amount of time clinicians spend sifting through patient notes and documenting in electronic health records (EHRs) is a leading cause of clinician burnout. By proactively and dynamically retrieving relevant notes during the documentation process, we can reduce the effort required to find relevant patient history. In this work, we conceptualize the use of EHR audit logs for machine learning as a source of supervision of note relevance in a specific clinical context, at a particular point in time. Our evaluation focuses on the dynamic retrieval in the emergency department, a high acuity setting with unique patterns of information retrieval and note writing. We show that our methods can achieve an AUC of 0.963 for predicting which notes will be read in an individual note writing session. We additionally conduct a user study with several clinicians and find that our framework can help clinicians retrieve relevant information more efficiently. Demonstrating that our framework and methods can perform well in this demanding setting is a promising proof of concept that they will translate to other clinical settings and data modalities (e.g., labs, medications, imaging). © 2023, CC BY.

关键词： Machine learning

Learning-based Calibration of Flux Crosstalk in Transmon Qubit Arrays

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Barrett, Cora N. Karamlou, Amir H. Muschinske, Sarah E. Rosen, Ilan T. Braumüller, Jochen Das, Rabindra Kim, David K. Niedzielski, Bethany M. Schuldt, Meghan Serniak, Kyle Schwartz, Mollie E. Yoder, Jonilyn L. Orlando, Terry P. Gustavsson, Simon Grover, Jeffrey A. Oliver, William D. Research Laboratory of Electronics Massachusetts Institute of Technology CambridgeMA02139 United States Department of Physics Wellesley College WellesleyMA02481 United States Department of Electrical Engineering and Computer Science Massachusetts Institute of Technology CambridgeMA02139 United States MIT Lincoln Laboratory LexingtonMA02421 United States Department of Physics Massachusetts Institute of Technology CambridgeMA02139 United States

Superconducting quantum processors comprising flux-tunable data and coupler qubits are a promising platform for quantum computation. However, magnetic flux crosstalk between the flux-control lines and the constituent qubits impedes precision control of qubit frequencies, presenting a challenge to scaling this platform. In order to implement high-fidelity digital and analog quantum operations, one must characterize the flux crosstalk and compensate for it. In this work, we introduce a learning-based calibration protocol and demonstrate its experimental performance by calibrating an array of 16 flux-tunable transmon qubits. To demonstrate the extensibility of our protocol, we simulate the crosstalk matrix learning procedure for larger arrays of transmon qubits. We observe an empirically linear scaling in calibration time with system size while maintaining a median qubit frequency error below 300 kHz. © 2023, CC0.

关键词： Crosstalk

Wireless for Machine Learning: a Survey

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Hellström, Henrik da Silva, José Mairton Barros Amiri, Mohammad Mohammadi Chen, Mingzhe Fodor, Viktoria Vincent Poor, H. Fischione, Carlo KTH - Royal Institute of Technology School of Electrical Engineering and Computer Science Sweden MIT - Massachusetts Institute of Technology MIT Media Laboratory United States Princeton University Department of Electrical and Computer Engineering United States

As data generation increasingly takes place on devices without a wired connection, machine learning (ML) related traffic will be ubiquitous in wireless networks. Many studies have shown that traditional wireless protocols are highly inefficient or unsustainable to support ML, which creates the need for new wireless communication methods. In this survey, we give an exhaustive review of the state-of-the-art wireless methods that are specifically designed to support ML services over distributed datasets. Currently, there are two clear themes within the literature, analog over-the-air computation and digital radio resource management optimized for ML. This survey gives a comprehensive introduction to these methods, reviews the most important works, highlights open problems, and discusses application scenarios. Copyright © 2020, The Authors. All rights reserved.

关键词： Machine learning

Informationally overcomplete POVMs for quantum state estimation and binary detection

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Medlock, Catherine Oppenheim, Alan Boufounos, Petros MIT Department of Electrical Engineering and Computer Science United States Mitsubishi Electric Research Laboratories Japan

Our intention while preparing these notes has been for them to be readable and interesting to an audience with a wide range of backgrounds. We anticipate that some sections will be familiar to readers with a strong background in classical signal processing and particularly in frame theory, and other sections to readers with a strong background in quantum mechanics. It is our hope that both audiences will find the perspectives in the shared issues and overlap between the two fields to be interesting. Copyright © 2020, The Authors. All rights reserved.

关键词： Quantum theory

Incremental Non-Gaussian Inference for SLAM Using Normalizing Flows

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Huang, Qiangqiang Pu, Can Khosoussi, Kasra Rosen, David M. Fourie, Dehann How, Jonathan P. Leonard, John J. MIT Computer Science and Artificial Intelligence Laboratory CambridgeMA02139 United States MIT Department of Nuclear Science and Engineering CambridgeMA02139 United States Robotics and Autonomous Systems Group DATA61 CSIRO BrisbaneQLD4069 Australia Northeastern University Department of Electrical and Computer Engineering BostonMA02115 United States NavAbility BostonMA02110 United States MIT Department of Aeronautical and Astronautical Engineering CambridgeMA02139 United States

This paper presents normalizing flows for incremental smoothing and mapping (NF-iSAM), a novel algorithm for inferring the full posterior distribution in SLAM problems with nonlinear measurement models and non-Gaussian factors. NF-iSAM exploits the expressive power of neural networks, and trains normalizing flows to model and sample the full posterior. By leveraging the Bayes tree, NF-iSAM enables efficient incremental updates similar to iSAM2, albeit in the more challenging non-Gaussian setting. We demonstrate the advantages of NF-iSAM over state-of-the-art point and distribution estimation algorithms using range-only SLAM problems with data association ambiguity. NF-iSAM presents superior accuracy in describing the posterior beliefs of continuous variables (e.g., position) and discrete variables (e.g., data association). Copyright © 2021, The Authors. All rights reserved.

关键词： Gaussian noise (electronic)

Space ants: Constructing and reconfiguring large-scale structures with finite automata 36

学校读者我要写书评

暂无评论

Space ants: Constructing and reconfiguring large-scale struc...

36th International Symposium on Computational Geometry, SoCG 2020

作者： Abdel-Rahman, Amira Becker, Aaron T. Biediger, Daniel E. Cheung, Kenneth C. Fekete, Sándor P. Gershenfeld, Neil A. Hugo, Sabrina Jenett, Benjamin Keldenich, Phillip Niehs, Eike Rieck, Christian Schmidt, Arne Scheffer, Christian Yannuzzi, Michael Center for Bits and Atoms MIT CambridgeMA United States Department of Electrical and Computer Engineering University of Houston TX United States Coded Structures Lab NASA Ames Research Center Moffett FieldCA United States Department of Computer Science TU Braunschweig Germany

ISBN: (纸本)9783959771436

In this video, we consider recognition and reconfiguration of lattice-based cellular structures by very simple robots with only basic functionality. The underlying motivation is the construction and modification of space facilities of enormous dimensions, where the combination of new materials with extremely simple robots promises structures of previously unthinkable size and flexibility. We present algorithmic methods that are able to detect and reconfigure arbitrary polyominoes, based on finite-state robots, while also preserving connectivity of a structure during reconfiguration. Specific results include methods for determining a bounding box, scaling a given arrangement, and adapting more general algorithms for transforming polyominoes. © Amira Abdel-Rahman, Aaron T. Becker, Daniel E. Biediger, Kenneth C. Cheung, Sándor P. Fekete, Neil A. Gershenfeld, Sabrina Hugo, Benjamin Jenett, Phillip Keldenich, Eike Niehs, Christian Rieck, Arne Schmidt, Christian Scheffer, and Michael Yannuzzi;licensed under Creative Commons License CC-BY 36th International Symposium on Computational Geometry (SoCG 2020).

关键词： Robots

Extremal graphs for a spectral inequality on edge-disjoint spanning trees

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Cioabă, Sebastian M. Ostuni, Anthony Park, Davin Potluri, Sriya Wakhare, Tanay Wong, Wiseley University of Delaware NewarkDE19716 United States University of Maryland College ParkMD20878 United States Department of Electrical Engineering and Computer Science MIT CambridgeMA02139 United States

Liu, Hong, Gu, and Lai proved if the second largest eigenvalue of the adjacency matrix of graph G with minimum degree δ ≥ 2m + 2 ≥ 4 satisfies λ2(G) m,d for all d ≥ 2m + 2 ≥ 4 with at most m edge-disjoint spanni... 详细信息

关键词： Eigenvalues and eigenfunctions

Semi-supervised spoken language understanding via self-supervised speech and language model pretraining

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Lai, Cheng-I Chuang, Yung-Sung Lee, Hung-Yi Li, Shang-Wen Glass, James MIT Computer Science and Artificial Intelligence Laboratory United States College of Electrical Engineering and Computer Science National Taiwan University Taiwan Amazon AI

Much recent work on Spoken Language Understanding (SLU) is limited in at least one of three ways: models were trained on oracle text input and neglected ASR errors, models were trained to predict only intents without the slot values, or models were trained on a large amount of in-house data. In this paper, we propose a clean and general framework to learn semantics directly from speech with semi-supervision from transcribed or untranscribed speech to address these issues. Our framework is built upon pretrained end-to-end (E2E) ASR and self-supervised language models, such as BERT, and fine-tuned on a limited amount of target SLU data. We study two semi-supervised settings for the ASR component: supervised pretraining on transcribed speech, and unsupervised pretraining by replacing the ASR encoder with self-supervised speech representations, such as wav2vec. In parallel, we identify two essential criteria for evaluating SLU models: environmental noise-robustness and E2E semantics evaluation. Experiments on ATIS show that our SLU framework with speech as input can perform on par with those using oracle text as input in semantics understanding, even though environmental noise is present and a limited amount of labeled semantics data is available for training. Copyright © 2020, The Authors. All rights reserved.

关键词： Speech recognition

Improving qubit coherence using closed-loop feedback

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Vepsäläinen, Antti Winik, Roni Karamlou, Amir H. Braumüller, Jochen Di Paolo, Agustin Sung, Youngkyu Kannan, Bharath Kjaergaard, Morten Kim, David K. Melville, Alexander J. Niedzielski, Bethany M. Yoder, Jonilyn L. Gustavsson, Simon Oliver, William D. Research Laboratory of Electronics Massachusetts Institute of Technology United States Department of Electrical Engineering and Computer Science Massachusetts Institute of Technology United States Center for Quantum Devices University of Copenhagen Denmark MIT Lincoln Laboratory

Superconducting qubits are a promising platform for building a larger-scale quantum processor capable of solving otherwise intractable problems. In order for the processor to reach practical viability, the gate errors need to be further suppressed and remain stable for extended periods of time. With recent advances in qubit control, both single- and two-qubit gate fidelities are now in many cases limited by the coherence times of the qubits. Here we experimentally employ closed-loop feedback to stabilize the frequency fluctuations of a superconducting transmon qubit, thereby increasing its coherence time by 26% and reducing the single-qubit error rate from (8.5 ±2.1) ×10−4 to (5.9 ± 0.7) × 10−4. Importantly, the resulting high-fidelity operation remains effective even away from the qubit flux-noise insensitive point, significantly increasing the frequency bandwidth over which the qubit can be operated with high fidelity. This approach is helpful in large qubit grids, where frequency crowding and parasitic interactions between the qubits limit their performance. © 2021, CC BY.

关键词： Feedback