检索结果-内蒙古大学图书馆

Proceedings of the 41st International Conference on Machine Learning

作者： Michelle Pan Mariah Schrum Vivek Myers Erdem Biyik Anca Dragan Department of Electrical Engineering and Computer Sciences UC Berkeley Department of Computer Science University of Southern California

Adaptive brain stimulation can treat neurological conditions such as Parkinson's disease and post-stroke motor deficits by influencing abnormal neural activity. Because of patient heterogeneity, each patient requires a unique stimulation policy to achieve optimal neural responses. Model-free reinforcement learning (MFRL) holds promise in learning effective policies for a variety of similar control tasks, but is limited in domains like brain stimulation by a need for numerous costly environment interactions. In this work we introduce Coprocessor Actor Critic, a novel, model-based reinforcement learning (MBRL) approach for learning neural coprocessor policies for brain stimulation. Our key insight is that coprocessor policy learning is a combination of learning how to act optimally in the world and learning how to induce optimal actions in the world through stimulation of an injured brain. We show that our approach overcomes the limitations of traditional MFRL methods in terms of sample efficiency and task success and outperforms baseline MBRL approaches in a neurologically realistic model of an injured brain.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Autonomous On-Device Protocols: Empowering Wireless with Self-Driven Capabilities

Autonomous On-Device Protocols: Empowering Wireless with Sel...

引用

IEEE Conference on Wireless Communications and Networking

作者： Hannaneh B. Pasandi Tamer Nadeem Department of Electrical Engineering and Computer Sciences UC Berkeley Department of Computer Science Virginia Commonwealth University

ISBN: (数字)9798350303582

ISBN: (纸本)9798350303599

This paper presents a study on applying on-device machine learning (ML) algorithms to enhance MAC layer protocols in wireless communications. It focuses on the MU-MIMO Grouping algorithm and explores the benefits of executing ML models directly on devices such as computers, smartphones, and IoT devices. This approach promises improved speed, privacy, security, and adaptability in dynamic networks. The paper evaluates the effectiveness of this strategy in Wi-Fi and Mas-sive MIMO scenarios, demonstrating significant system capacity enhancement, latency reduction, and improved user experience. Additionally, it examines the interaction between on-device ML and changing network environments, underscoring the method's adaptability and robustness. This research represents a significant advancement in MAC layer protocols using on-device ML and may inspire future innovations in wireless networks.

关键词： Technological innovation Protocols Machine learning algorithms Wireless networks Heuristic algorithms Media Access Protocol User experience

来源：评论

学校读者我要写书评

暂无评论

Forecasting Aortic Pressure Cross-Cohort with Deep Sequence Models

Forecasting Aortic Pressure Cross-Cohort with Deep Sequence ...

引用

2022 Computing in Cardiology, CinC 2022

作者： Li, Alan Zhou, Zihao Jortberg, Elise Yu, Rose Department of Computer Science and Engineering Uc San Diego United States Abiomed DanversMA United States

ISBN: (纸本)9798350300970

Mean aortic pressure (MAP) is a primary measurement for monitoring blood and O2 delivery to major organs. Prolonged periods of hypotension, low MAP, lead to low tissue perfusion and subsequent end organ damage. Patients on mechanical circulatory support (MCS) devices, such as the Impella CP, are managed to maintain sufficient MAP for end-organ perfusion. Forecasting MAP is important for early warning of clinically concerning events, including hypotension and instability as well as device weaning. Patients presenting with cardiogenic shock as a result of acute myocardial infarction (AMI/CGS) have increased hemodynamic instability when compared to patients undergoing high-risk percutaneous coronary interventions (HRPCI). Existing deep sequence models for fore-casting often focus on the same patient cohort and cannot generalize across cohorts. In this paper, we examine how deep sequence models respond to the distribution shift of the MAP across the MCS patient cohorts during forecasting. We propose conditional RNN, a deep sequence model that learns to adapt to a different cohort by conditioning on time-invariant cohort features. Our proposed model improves the forecasting performance, achieving a 5.2 mmHg - 6.1 mmHg RMSE for cross-cohort patients. © 2022 Creative Commons.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Diode-Triode Current Mirror Inverter PUF: A Novel Mixed-Signal Low Power Analog PUF 66

Diode-Triode Current Mirror Inverter PUF: A Novel Mixed-Sign...

引用

2023 IEEE 66th International Midwest Symposium on Circuits and Systems, MWSCAS 2023

作者： Gisha, C.G. Chakraborty, Ananda Sankar Chakraborty, Rajat Subhra Jose, Bijoy Antony Mathew, Jimson Cochin University of Science and Technology Department of Electronics Kochi India Berkeley Wireless Research Center Uc Berkeley Berkeley United States Iit Department of Computer Science and Engineering Kharagpur India Cochin University of Science and Technology Department of Computer Science Kochi India Indian Institute of Technology Patna Department of Computer Science Bihar India

ISBN: (纸本)9798350302103

Physically Unclonable Function (PUF) is a useful and versatile lightweight hardware security primitive that takes advantage of unavoidable and unpredictable random process variations during chip manufacturing. This paper proposes a novel diode-triode low-power analog PUF circuit on CMOS current mirror inverter circuit. Due to the random process variation of the MOSFET parameters, the output voltage level of the inverter will vary based on the applied input. These analog voltage variations in the circuit output are converted into a corresponding digital response through an XOR-tree. The performance metrics of the proposed PUF circuit were estimated by simulating a 64-bit PUF circuit at a 32-nano m CMOS technology node. The proposed PUF design achieves a uniformity of 49.87%, an inter-Hamming Distance of 47.52%, average bitaliasing of 49.87%, while consuming 20.99 μW power during operation. The proposed PUF also shows excellent robustness to machine learning based modeling attacks. © 2023 IEEE.

关键词： analog PUF current mirror inverter hardware security low power Mixed-signal PUF

来源：评论

学校读者我要写书评

暂无评论

Corners in Quasirandom Groups via Sparse Mixing

arXiv

引用

arXiv 2024年

作者： Jaber, Michael Lovett, Shachar Ostuni, Anthony Department of Computer Science UT Austin United States Department of Computer Science and Engineering UC San Diego United States

We improve the best known upper bounds on the density of corner-free sets over quasirandom groups from inverse poly-logarithmic to quasi-polynomial. We make similarly substantial improvements to the best known lower bounds on the communication complexity of a large class of permutation functions in the 3-player Number-on-Forehead model. Underpinning both results is a general combinatorial theorem that extends the recent work of Kelley, Lovett, and Meka (STOC’24), itself a development of ideas from the breakthrough result of Kelley and Meka on three-term arithmetic progressions (FOCS’23). © 2024, CC BY.

关键词： Combinatorial mathematics

来源：评论

学校读者我要写书评

暂无评论

Conflict-Averse Gradient Optimization of Ensembles for Effective Offline Model-Based Optimization

arXiv

引用

arXiv 2023年

作者： Kolli, Sathvik UC Berkeley Electrical Engineering & Computer Science United States

Data-driven offline model-based optimization (MBO) is an established practical approach to black-box computational design problems for which the true objective function is unknown and expensive to query. However, the standard approach which optimizes designs against a learned proxy model of the ground truth objective can suffer from distributional shift. Specifically, in high-dimensional design spaces where valid designs lie on a narrow manifold, the standard approach is susceptible to producing out-of-distribution, invalid designs that "fool" the learned proxy model into outputting a high value. Using an ensemble rather than a single model as the learned proxy can help mitigate distribution shift, but naive formulations for combining gradient information from the ensemble, such as minimum or mean gradient, are still suboptimal and often hampered by non-convergent behavior. © 2023, CC BY.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Learning Stabilization Control from Observations by Learning Lyapunov-like Proxy Models

Learning Stabilization Control from Observations by Learning...

引用

IEEE International Conference on Robotics and Automation (ICRA)

作者： Milan Ganai Chiaki Hirayama Ya-Chien Chang Sicun Gao Department of Computer Science and Engineering UC San Diego USA

The deployment of Reinforcement Learning to robotics applications faces the difficulty of reward engineering. Therefore, approaches have focused on creating reward functions by Learning from Observations (LfO) which is the task of learning policies from expert trajectories that only contain state sequences. We propose new methods for LfO for the important class of continuous control problems of learning to stabilize, by introducing intermediate proxy models acting as reward functions between the expert and the agent policy based on Lyapunov stability theory. Our LfO training process consists of two steps. The first step attempts to learn a Lyapunov-like landscape proxy model from expert state sequences without access to any kinematics model, and the second step uses the learned landscape model to guide in training the learner's policy. We formulate novel learning objectives for the two steps that are important for overall training success. We evaluate our methods in real automobile robot environments and other simulated stabilization control problems in model-free settings, like Quadrotor control and maintaining upright positions of Hopper in MuJoCo. We compare with state-of-the-art approaches and show the proposed methods can learn efficiently with less expert observations.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Conformal Decision Theory: Safe Autonomous Decisions from Imperfect Predictions

Conformal Decision Theory: Safe Autonomous Decisions from Im...

引用

IEEE International Conference on Robotics and Automation (ICRA)

作者： Jordan Lekeufack Anastasios N. Angelopoulos Andrea Bajcsy Michael I. Jordan Jitendra Malik Department of Statistics UC Berkeley Department of Electrical Engineering and Computer Science UC Berkeley Robotics Institute Carnegie Mellon University

ISBN: (数字)9798350384574

ISBN: (纸本)9798350384581

We introduce Conformal Decision Theory, a framework for producing safe autonomous decisions despite imperfect machine learning predictions. Examples of such decisions are ubiquitous, from robot planning algorithms that rely on pedestrian predictions, to calibrating autonomous manufacturing to exhibit high throughput and low error, to the choice of trusting a nominal policy versus switching to a safe backup policy at run-time. The decisions produced by our algorithms are safe in the sense that they come with provable statistical guarantees of having low risk without any assumptions on the world model whatsoever; the observations need not be I.I.D. and can even be adversarial. The theory extends results from conformal prediction to calibrate decisions directly, without requiring the construction of prediction sets. Experiments demonstrate the utility of our approach in robot motion planning around humans and robot manufacturing.

关键词： Robot motion Pedestrians Machine learning algorithms Decision theory Switches Prediction algorithms Throughput

来源：评论

学校读者我要写书评

暂无评论

Uncertainty Quantification Using Subsampling for Assembly-Free Estimates of Genomic Distance and Phylogenetic Relationships 26th

Uncertainty Quantification Using Subsampling for Assembly-F...

引用

26th International Conference on Research in Computational Molecular Biology, RECOMB 2022

作者： Rachtman, Eleonora Sarmashghi, Shahab Bafna, Vineet Mirarab, Siavash Bioinformatics and Systems Biology Graduate Program UC San Diego La JollaCA United States Department of Electrical and Computer Engineering UC San Diego La JollaCA United States Department of Computer Science and Engineering UC San Diego La JollaCA United States

Computing the distance between two genomes, often without using alignments or even access to assembled sequences, is fundamental to many downstream analyses. © 2022, The Author(s), under exclusive license to Spri... 详细信息

ISBN: (纸本)9783031047480

关键词： Uncertainty analysis

来源：评论

学校读者我要写书评

暂无评论

Can SAM recognize crops? Quantifying the zero-shot performance of a semantic segmentation foundation model on generating crop-type maps using satellite imagery for precision agriculture

arXiv

引用

arXiv 2023年

作者： Gurav, Rutuja Patel, Het Shang, Zhuocheng Eldawy, Ahmed Chen, Jia Scudiero, Elia Papalexakis, Evangelos Department of Computer Science and Engineering UC Riverside United States Environmental Sciences Department UC Riverside United States Department of Electrical and Computer Engineering UC Riverside United States

Climate change is increasingly disrupting worldwide agriculture, making global food production less reliable. To tackle the growing challenges in feeding the planet, cutting-edge management strategies, such as precision agriculture, empower farmers and decision-makers with rich and actionable information to increase the efficiency and sustainability of their farming practices. Crop-type maps are key information for decision-support tools but are challenging and costly to generate. We investigate the capabilities of Meta AI's Segment Anything Model (SAM) for crop-map prediction task, acknowledging its recent successes at zero-shot image segmentation. However, SAM being limited to up-to 3 channel inputs and its zero-shot usage being class-agnostic in nature pose unique challenges in using it directly for crop-type mapping. We propose using clustering consensus metrics to assess SAM's zero-shot performance in segmenting satellite imagery and producing crop-type maps. Although direct crop-type mapping is challenging using SAM in zero-shot setting, experiments reveal SAM's potential for swiftly and accurately outlining fields in satellite images, serving as a foundation for subsequent crop classification. This paper attempts to highlight a use-case of state-of-the-art image segmentation models like SAM for crop-type mapping and related specific needs of the agriculture industry, offering a potential avenue for automatic, efficient, and cost-effective data products for precision agriculture practices. Copyright © 2023, The Authors. All rights reserved.

关键词： Crops

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：