检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Zeger, Emi Wang, Yifei Mishkin, Aaron Ergen, Tolga Candès, Emmanuel Pilanci, Mert Stanford University United States Department of Electrical Engineering Department of Computer Science Departments of Statistics and Mathematics

We prove that training neural networks on 1-D data is equivalent to solving convex Lasso problems with discrete, explicitly defined dictionary matrices. We consider neural networks with piecewise linear activations and depths ranging from 2 to an arbitrary but finite number of layers. We first show that two-layer networks with piecewise linear activations are equivalent to Lasso models using a discrete dictionary of ramp functions, with breakpoints corresponding to the training data points. In certain general architectures with absolute value or ReLU activations, a third layer surprisingly creates features that reflect the training data about themselves. Additional layers progressively generate reflections of these reflections. The Lasso representation provides valuable insights into the analysis of globally optimal networks, elucidating their solution landscapes and enabling closed-form solutions in certain special cases. Numerical results show that reflections also occur when optimizing standard deep networks using standard non-convex optimizers. Additionally, we demonstrate our theory with autoregressive time series models. Copyright © 2024, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Sim-to-Real Robotic Sketching using Behavior Cloning and Reinforcement Learning

Sim-to-Real Robotic Sketching using Behavior Cloning and Rei...

引用

IEEE International Conference on Robotics and Automation (ICRA)

作者： Biao Jia Dinesh Manocha Department of Computer Science University of Maryland College Park MD Departments of Computer Science and Electrical & Computer Engineering University of Maryland College Park MD

ISBN: (数字)9798350384574

ISBN: (纸本)9798350384581

Robotic sketching in real-world scenarios poses a challenging problem with diverse applications in art, robotics, and digital design. We present a novel approach that bridges the gap between digital and robotic sketching, leveraging behavior cloning and reinforcement learning techniques. This paper introduces an approach aimed at bringing the gap between simulated and real-world robotic sketching closer together through the integration of behavior cloning and reinforcement learning techniques. Our approach trains painting policies that operate effectively in both virtual environments and real-world robotic sketching systems. We have implemented a robotic sketching system featuring an UltraArm robot equipped with a RealSense D415 camera, closely emulating the MyPaint virtual environment. Our system can perceive its environment and adapt painting policies to natural painting media. Our results highlight the effectiveness of our agent in terms of acquiring policies for high-dimensional continuous action spaces, enabling the seamless transfer of brush manipulation techniques from simulation to practical robotic sketching. Furthermore, we demonstrate our robotic sketching system’s capability to generate complex images and strokes using various configurations. https://***/view/sketchingrobot

关键词： Brushes Art Robot vision systems Cloning Virtual environments Reinforcement learning Media

来源：评论

学校读者我要写书评

暂无评论

Nanoparticle Deposition Techniques for Silica Nanoparticles: Synthesis, Electrophoretic Deposition, and Optimization- A review

arXiv

引用

arXiv 2025年

作者： Karmakar, Srabani Deo, Milind Rahaman, Imteaz Mohanty, Swomitra Kumar Department of Materials Science & Engineering University of Utah United States Departments of Chemical Engineering University of Utah United States Department of Electrical & Computer Engineering University of Utah United States Departments of Chemical Engineering Department of Materials Science Engineering University of Utah United States

Silica nanoparticles have emerged as key building blocks for advanced applications in electronics, catalysis, energy storage, biomedicine, and environmental science. In this review, we focus on recent developments in both the synthesis and deposition of these nanoparticles, emphasizing the widely used Stöber method and the versatile technique of electrophoretic deposition (EPD). The Stöber method is celebrated for its simplicity and reliability, offering precise control over particle size, morphology, and surface properties to produce uniform, monodisperse silica nanoparticles that meet high-quality standards for advanced applications. EPD, on the other hand, is a cost-effective, room-temperature process that enables uniform coatings on substrates with complex geometries. When compared to traditional techniques such as chemical vapor deposition, atomic layer deposition, and spin coating, EPD stands out due to its scalability, enhanced material compatibility, and ease of processing. Moreover, Future research should integrate AI-driven optimization with active learning to enhance electrophoretic deposition (EPD) of silica nanoparticles, leveraging predictive modeling and real-time adjustments for improved film quality and process efficiency. This approach promises to accelerate material discovery and enable scalable nanofabrication of advanced functional films. Copyright © 2025, The Authors. All rights reserved.

关键词： Spin coating

来源：评论

学校读者我要写书评

暂无评论

Improved Construction of Robust Gray Codes

arXiv

引用

arXiv 2024年

作者： Fathollahi, Dorsa Wootters, Mary Department of Electrical Engineering Stanford University StanfordCA United States Departments of Computer Science and Electrical Engineering Stanford University StanfordCA United States

A robust Gray code, formally introduced by (Lolck and Pagh, SODA 2024), is a Gray code that additionally has the property that, given a noisy version of the encoding of an integer j, it is possible to reconstruct ĵ so that |j − ĵ| is small with high probability. That work presented a transformation that transforms a binary code C of rate R to a robust Gray code with rate Ω(R), where the constant in the Ω(·) can be at most 1/4. We improve upon their construction by presenting a transformation from a (linear) binary code C to a robust Gray code with similar robustness guarantees, but with rate that can approach R/2. © 2024, CC BY.

关键词： Binary codes

来源：评论

学校读者我要写书评

暂无评论

Globally-consistent rule-based summary-explanations for machine learning models: application to credit-risk evaluation

The Journal of Machine Learning Research

引用

The Journal of Machine Learning Research 2023年第1期24卷 533-576页

作者： Cynthia Rudin Yaron Shaposhnik Departments of Computer Science and Electrical & Computer Engineering Duke University Durham NC Simon Business School University of Rochester Rochester NY

We develop a method for understanding specific predictions made by (global) predictive models by constructing (local) models tailored to each specific observation (these are also called "explanations" in the literature). Unlike existing work that "explains" specific observations by approximating global models in the vicinity of these observations, we fit models that are globally-consistent with predictions made by the global model on past data. We focus on rule-based models (also known as association rules or conjunctions of predicates), which are interpretable and widely used in practice. We design multiple algorithms to extract such rules from discrete and continuous datasets, and study their theoretical properties. Finally, we apply these algorithms to multiple credit-risk models trained on the Explainable Machine Learning Challenge data from FICO and demonstrate that our approach effectively produces sparse summary-explanations of these models in seconds. Our approach is model-agnostic (that is, can be used to explain any predictive model), and solves a minimum set cover problem to construct its summaries.

关键词： explainable artificial intelligence (XAI) local explanations interpretability credit risk

来源：评论

学校读者我要写书评

暂无评论

Design Concept of a Wearable Device for Sleep Related Brain Wave Detection and Stimulation 4

Design Concept of a Wearable Device for Sleep Related Brain ...

引用

4th IEEE International Conference on Data science and computer Application, ICDSCA 2024

作者： Yin, Ariel R. Zhang, David Z. Mao, David D. Li, Sichuang Cheng, Haoliang Deng, Yangfan Guo, Yifan Mao, Helen X. Yin, Jijun Mao, Zhi-Hong Canyon Crest Academy San DiegoCA United States University High School IrvineCA United States North Allegheny Intermediate High School PittsburghPA United States Department of Electrical and Computer Engineering University of Pittsburgh PittsburghPA United States Department of Computer Science University of Pittsburgh PittsburghPA United States Elmore Family School of Electrical and Computer Engineering Purdue University West LafayetteIN United States Yale College Yale University New HavenCT United States Departments of Electrical and Computer Engineering and Bioengineering University of Pittsburgh PittsburghPA United States

ISBN: (纸本)9798350368239

This paper presents a design concept of an innovative wearable device for brain wave detection and stimulation to aid sleep. Sleep’s importance for a healthy life emphasizes the value of studying the application of technology to improve sleep quality for individuals unable to receive a good night’s rest. Utilizing electroencephalography (EEG) for accurate sleep tracking, the device aims to be portable and efficient. It includes the EEG sensing and processing module, adaptive control and machine learning module, and electronic stimulation module, working together to guide the brain toward relaxation. Preliminary results demonstrate promising performances or necessities of the subsystems of the proposed design. ©2024 IEEE.

关键词： Sleep research

来源：评论

学校读者我要写书评

暂无评论

Microfluidic-organic thin film transistor coupled platform for simple solution exposure

RSC Applied Interfaces

引用

RSC Applied Interfaces 2024年第4期1卷 771-778页

作者： Boileau, Nicholas T. King, Benjamin Kapar, Sparsh Sohi, Ali Najafi Manion, Joseph G. Godin, Michel Lessard, Benoît H. Department of Chemical and Biological Engineering University of Ottawa 161 Louis Pasteur Pvt Ottawa ON Canada Department of Physics University of Ottawa 150 Louis Pasteur Pvt Ottawa ON Canada Ottawa-Carleton Institute for Biomedical Engineering University of Ottawa 161 Louis Pasteur Pvt Ottawa ON Canada School of Electrical Engineering and Computer Science University of Ottawa 800 King Edward Ave. Ottawa ON Canada

Efforts to combine organic thin film transistors (OTFTs) within microfluidic networks to create sensitive, versatile, and low-cost sensors for rapid chemical analysis have been limited by the need for complex equipment and by the sensitivity of OTFTs to common processing techniques used in traditional microfluidic fabrication. We designed and validated a robust, easy to use, and simple to manufacture prototype microfluidic-OTFT pressure coupled system. Our design enables multiple OTFT architectures to be combined with microfluidic analyte delivery, eliminates common processing steps that can alter OTFT performance, and only requires easily-accessible equipment. As a proof of concept, we demonstrate the exposure of aluminium chloride phthalocyanine (AlClPc) based OTFTs to different solutions of sodium fluoride (NaF). This work could accelerate the design of more versatile, rapid, and reliable OTFT based liquid chemical sensors. © 2024 RSC.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Quantifying Strain Dependence of Multi-Frequency Shearwave Elasticity Imaging

Quantifying Strain Dependence of Multi-Frequency Shearwave E...

引用

2023 IEEE Western New York Image and Signal Processing Workshop, WNYISPW 2023

作者： Khan, Siladitya Goswami, Soumya Feng, Fan Doyley, Marvin M. McAleavey, Stephen A. University of Rochester Departments of Biomedical and Computer Engineering RochesterNY14627 United States University of Rochester Rochester Center for Biomedical Ultrasound RochesterNY14627 United States University of Rochester Goergen Institute for Data Science RochesterNY14627 United States University of Rochester Departments of Electrical and Computer Engineering RochesterNY14627 United States

ISBN: (纸本)9798350329698

Nonlinear shear modulus (NLSM) can potentially differentiate benign and malignant pathologies. Previous studies demonstrated the discriminatory value of mapping quantitative estimates of material non-linearity, yet estimates remain biased due to unaccounted shear-wave dispersion within the tissue. We demonstrate a finite element simulation of an inversion technique that combines traditional quasi-static and dynamic elasticity imaging to generate a multi-frequency estimate of the third-order shear modulus A(x,z,ω) over a broad bandwidth (200-600 Hz). We show that our reconstruction results are superior to those obtained by traditional group speed by a factor of two in terms of contrast enhancement measures. Experimental ultrasound elastography on a custom oil-in-gelatin emulsion confirms the presence of dispersion in the NLSM parameter. Constitutive hyper-viscoelastic model responses of spectral NLSM are simulated based on matched linear shear modulus data of experimental phantoms. Hyper-elastic Ogden with a Voigt loss is shown to describe NLSM behavior at frequencies greater than 400 Hz. Reconstruction accuracy in the presence of simulated tracking and correlation noise demonstrates the robustness of our estimates. © 2023 IEEE.

关键词： Elastic moduli

来源：评论

学校读者我要写书评

暂无评论

Development of an Adaptive Artifact Subspace Reconstruction Based on Hebbian/Anti-Hebbian Learning Networks for Enhancing BCI Performance

引用

IEEE Transactions on Neural Networks and Learning Systems 2024年第1期35卷 348-361页

作者： Tsai, Bo-Yu Diddi, Sandeep Vara Sankar Ko, Li-Wei Wang, Shuu-Jiun Chang, Chi-Yuan Jung, Tzyy-Ping Institute of Biomedical Engineering and the Brain Research Center National Yang Ming Chiao Tung University Hsinchu300 Taiwan Hsinchu300 Taiwan College of Biological Science and Technology National Yang Ming Chiao Tung University Hsinchu300 Taiwan Institute of Electrical and Control Engineering Institute of Biomedical Engineering Brain Research Center College of Electrical and Computer Engineering National Yang Ming Chiao Tung University Department of Electronics and Electrical Engineering Hsinchu300 Taiwan Kaohsiung Medical University Department of Biomedical Science and Environment Biology Drug Development and Value Creation Research Center Kaohsiung807 Taiwan Taipei Veterans General Hospital Taipei11217 Taiwan National Yang Ming Chiao Tung University Brain Research Center School of Medicine Taipei112 Taiwan University of California San Diego Swartz Center for Computational Neuroscience San DiegoCA92093 United States

Brain-computer interface (BCI) actively translates the brain signals into executable actions by establishing direct communication between the human brain and external devices. Recording brain activity through electroencephalography (EEG) is generally contaminated with both physiological and nonphysiological artifacts, which significantly hinders the BCI performance. Artifact subspace reconstruction (ASR) is a well-known statistical technique that automatically removes artifact components by determining the rejection threshold based on the initial reference EEG segment in multichannel EEG recordings. In real-world applications, the fixed threshold may limit the efficacy of the artifact correction, especially when the quality of the reference data is poor. This study proposes an adaptive online ASR technique by integrating the Hebbian/anti-Hebbian neural networks into the ASR algorithm, namely, principle subspace projection ASR (PSP-ASR) and principal subspace whitening ASR (PSW-ASR) that segmentwise self-organize the artifact subspace by updating the synaptic weights according to the Hebbian and anti-Hebbian learning rules. The effectiveness of the proposed algorithm is compared to the conventional ASR approaches on benchmark EEG dataset and three BCI frameworks, including steady-state visual evoked potential (SSVEP), rapid serial visual presentation (RSVP), and motor imagery (MI) by evaluating the root-mean-square error (RMSE), the signal-to-noise ratio (SNR), the Pearson correlation, and classification accuracy. The results demonstrated that the PSW-ASR algorithm effectively removed the EEG artifacts and retained the activity-specific brain signals compared to the PSP-ASR, standard ASR (Init-ASR), and moving-window ASR (MW-ASR) methods, thereby enhancing the SSVEP, RSVP, and MI BCI performances. Finally, our empirical results from the PSW-ASR algorithm suggested the choice of an aggressive cutoff range of c =1-10 for activity-specific BCI applications and a moderat

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

Navigable Areas Segmentation Method for Unmanned Surface Vehicles in Paddy Fields 11

Navigable Areas Segmentation Method for Unmanned Surface Veh...

引用

11th IEEE Region 10 Humanitarian Technology Conference, R10-HTC 2023

作者： Machida, Kentaro Nakamura, Tetsuya Cai, Jingyong Nguyen-Quang, Thinh Pham, Duc Anh Huy-Dung, Han Nguyen, Huy Hoang Ookawa, Taiichiro Nakajo, Hironori Tokyo University of Agriculture and Technology Dept. of Electrical Engineering and Computer Science Tokyo Japan Yukimai Design Co. Ltd. Tokyo Japan School of Electrical and Electronic Engineering Hanoi University of Science and Technology Hanoi Viet Nam Tokyo University of Agriculture and Technology Dept. of Biological Production Tokyo Japan

ISBN: (纸本)9798350326147

An Unmanned Surface Vehicle (USV) capable of automatic navigation in paddy fields could enhance paddy rice cultivation efficiency. However, flexible navigation is challenging with rule-based methods. This study introduce a deep neural network-based navigable area binary segmentation method, utilizing images from a front camera mounted on a USV. Evaluation with a newly created dataset confirmed that this method could flexibly segment navigable areas, even in rice fields where rule-based methods struggle. © 2023 IEEE.

关键词： Unmanned surface vehicles

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：