检索结果-内蒙古大学图书馆

您好，读者！请登录

内蒙古大学图书馆

首页
概况
党建
资源
服务
科研支持
- 论文收录引用证明
- 科技查新
知识产权
档案馆
帮助

咨询与建议

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

您的常用邮箱：*

您的手机号码：*

问题描述：

当前已输入0个字，您还可以输入200个字

全部搜索
期刊论文
图书
学位论文
标准
纸本馆藏
外文资源发现
数据库导航
超星发现

高级检索

时间限定

出版年份：

文献类型

图书期刊文献学位论文多媒体

馆藏选择

电子馆藏纸本馆藏

核心期刊

全部期刊 SCI 收录期刊 SSCI 收录期刊 EI 收录期刊 CSCD 收录期刊 CSSCI 收录期刊

语言

中文英文

文献类型

期刊文献图书学位论文标准纸本馆藏

帮助

文字说明：

T=题名（书名、题名），A=作者（责任者），K=主题词，P=出版物名称，PU=出版社名称，O=机构（作者单位、学位授予单位、专利申请人），L=中图分类号，C=学科分类号，U=全部字段，Y=年（出版发行年、学位年度、标准发布年）

检索规则说明：

AND代表“并且”；OR代表“或者”；NOT代表“不包含”；(注意必须大写,运算符两边需空一格)

检索范例：

范例一：(K=图书馆学 OR K=情报学) AND A=范并思 AND Y=1982-2016
范例二：P=计算机应用与软件 AND (U=C++ OR U=Basic) NOT K=Visual AND Y=2011-2016

分类表

所选分类

>> <<

限定检索结果

文献类型

698 篇 期刊文献
689 篇 会议
4 册 图书

馆藏范围

1,391 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

844 篇 工学
- 336 篇 计算机科学与技术...
- 267 篇 软件工程
- 239 篇 电子科学与技术（可...
- 201 篇 电气工程
- 150 篇 光学工程
- 137 篇 信息与通信工程
- 103 篇 材料科学与工程（可...
- 99 篇 控制科学与工程
- 94 篇 生物工程
- 83 篇 生物医学工程（可授...
- 78 篇 化学工程与技术
- 62 篇 仪器科学与技术
- 59 篇 力学（可授工学、理...
- 38 篇 动力工程及工程热...
- 36 篇 机械工程
- 28 篇 土木工程
709 篇 理学
- 378 篇 物理学
- 239 篇 数学
- 115 篇 生物学
- 93 篇 统计学（可授理学、...
- 85 篇 化学
- 61 篇 系统科学
- 40 篇 地球物理学
100 篇 管理学
- 71 篇 管理科学与工程(可...
- 34 篇 工商管理
- 30 篇 图书情报与档案管...
59 篇 医学
- 42 篇 临床医学
- 38 篇 基础医学(可授医学...
- 28 篇 药学(可授医学、理...
29 篇 法学
15 篇 经济学
13 篇 农学
12 篇 教育学
10 篇 文学
5 篇 军事学
1 篇 哲学
1 篇 历史学

主题

24 篇 machine learning
21 篇 computer science
17 篇 computational mo...
16 篇 decoding
13 篇 costs
12 篇 polynomials
12 篇 testing
11 篇 optical pulses
11 篇 silicon
11 篇 humans
11 篇 electrodes
11 篇 artificial intel...
10 篇 nonlinear optics
10 篇 voltage
10 篇 laboratories
10 篇 optimization
10 篇 trajectory
10 篇 hardware
10 篇 forecasting
9 篇 qubits

机构

71 篇 department of el...
63 篇 department of el...
52 篇 department of el...
50 篇 department of el...
43 篇 department of el...
41 篇 mit dep of elect...
33 篇 research laborat...
31 篇 department of el...
30 篇 department of ph...
28 篇 department of ph...
28 篇 dunlap institute...
28 篇 department of ph...
27 篇 lane department ...
27 篇 center for gravi...
25 篇 department of el...
25 篇 mit lincoln labo...
24 篇 department of ph...
24 篇 mit kavli instit...
23 篇 david a. dunlap ...
23 篇 department of el...

作者

29 篇 oliver william d...
26 篇 jaillet patrick
24 篇 gustavsson simon
23 篇 bandura kevin
23 篇 mena-parra juan
21 篇 leung calvin
21 篇 niedzielski beth...
20 篇 cassanelli tomas
19 篇 gaensler b.m.
19 篇 rahman mubdi
19 篇 brar charanjot
19 篇 orlando terry p.
18 篇 pearlman aaron b...
18 篇 rafiei-ravandi m...
18 篇 shin kaitlyn
18 篇 vanderlinde keit...
18 篇 yoder jonilyn l.
17 篇 adalsteinsson el...
17 篇 sanghavi pranav
17 篇 dobbs matt

语言

1,316 篇 英文
64 篇 其他
11 篇 中文

检索条件"机构=Electrical Engineering and Computer Science/MIT"

共 1391 条记录，以下是11-20 订阅

全选清除本页清除全部题录导出标记到"检索档案"

详细简洁

排序：

Consistent Diffusion Meets Tweedie: Training Exact Ambient Diffusion Models with Noisy Data 41

Consistent Diffusion Meets Tweedie: Training Exact Ambient D...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Daras, Giannis Dimakis, Alexandros G. Daskalakis, Constantinos Department of Computer Science University of Texas Austin United States Archimedes AI United States Department of Electrical and Computer Engineering University of Texas Austin United States Department of Electrical Engineering and Computer Science MIT United States

Ambient diffusion is a recently proposed framework for training diffusion models using corrupted data. Both Ambient Diffusion and alternative SURE-based approaches for learning diffusion models from corrupted data resort to approximations which deteriorate performance. We present the first framework for training diffusion models that provably sample from the uncorrupted distribution given only noisy training data, solving an open problem in Ambient diffusion. Our key technical contribution is a method that uses a double application of Tweedie's formula and a consistency loss function that allows us to extend sampling at noise levels below the observed data noise. We also provide further evidence that diffusion models memorize from their training sets by identifying extremely corrupted images that are almost perfectly reconstructed, raising copyright and privacy concerns. Our method for training using corrupted samples can be used to mitigate this problem. We demonstrate this by fine-tuning Stable Diffusion XL to generate samples from a distribution using only noisy samples. Our framework reduces the amount of memorization of the fine-tuning dataset, while maintaining competitive performance. Copyright 2024 by the author(s)

关键词： Problem solving

来源：评论

学校读者我要写书评

暂无评论

Web Based Book Recommendation System Using Collaborative Filtering 5

Web Based Book Recommendation System Using Collaborative Fil...

引用

5th International Conference on Emerging Smart Computing and Informatics, ESCI 2023

作者： Mankar, Ketaki Pawar, Shruti Agarwal, Harsh Sangale, Tejas Kulkarni, Smita Mit Academy of Engineering Department of Computer Science Engineering Pune India Mit Academy of Engineering Department of Electronics and Electrical Engineering Pune India

ISBN: (纸本)9781665475242

Recommender systems are tools that help end users recommend products and obtain information about their preferences by going online. Today's online bookstores compete with each other in a variety of ways. One of the most powerful ways to efficiently increase revenue by attracting customers is a referral system. This study offers a clear, understandable method for recommending books that aids readers in selecting the best book. The proposed methodology works on training of database and feedback to provide meaningful information that helps users make decisions. In this paper recommendation system is developed by using collaborative filtering method. The machine learning (ML) model KNN is proposed to categorize the books as per user preferences. The overall architecture of the proposed system is introduced and its implementation is demonstrated. © 2023 IEEE.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

RISK-AWARE REINFORCEMENT LEARNING WITH COHERENT RISK MEASURES AND NON-LINEAR FUNCTION APPROXIMATION 11

RISK-AWARE REINFORCEMENT LEARNING WITH COHERENT RISK MEASURE...

引用

11th International Conference on Learning Representations, ICLR 2023

作者： Lam, Thanh Verma, Arun Low, Bryan Kian Hsiang Jaillet, Patrick Department of Computer Science National University of Singapore Singapore Department of Electrical Engineering and Computer Science MIT United States

We study the risk-aware reinforcement learning (RL) problem in the episodic finite-horizon Markov decision process with unknown transition and reward functions. In contrast to the risk-neutral RL problem, we consider minimizing the risk of having low rewards, which arise due to the intrinsic randomness of the MDPs and imperfect knowledge of the model. Our work provides a unified framework to analyze the regret of risk-aware RL policy with coherent risk measures in conjunction with non-linear function approximation, which gives the first sub-linear regret bounds in the setting. Finally, we validate our theoretical results via empirical experiments on synthetic and real-world data. © 2023 11th International Conference on Learning Representations, ICLR 2023. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

FEDERATED NEURAL BANDITS 11

FEDERATED NEURAL BANDITS

引用

11th International Conference on Learning Representations, ICLR 2023

作者： Dai, Zhongxiang Shu, Yao Verma, Arun Fan, Flint Xiaofeng Low, Bryan Kian Hsiang Jaillet, Patrick Department of Computer Science National University of Singapore Singapore Department of Electrical Engineering and Computer Science MIT United States

Recent works on neural contextual bandits have achieved compelling performances due to their ability to leverage the strong representation power of neural networks (NNs) for reward prediction. Many applications of contextual bandits involve multiple agents who collaborate without sharing raw observations, thus giving rise to the setting of federated contextual bandits. Existing works on federated contextual bandits rely on linear or kernelized bandits, which may fall short when modeling complex real-world reward functions. So, this paper introduces the federated neural-upper confidence bound (FN-UCB) algorithm. To better exploit the federated setting, FN-UCB adopts a weighted combination of two UCBs: UCBa allows every agent to additionally use the observations from the other agents to accelerate exploration (without sharing raw observations), while UCBb uses an NN with aggregated parameters for reward prediction in a similar way to federated averaging for supervised learning. Notably, the weight between the two UCBs required by our theoretical analysis is amenable to an interesting interpretation, which emphasizes UCBa initially for accelerated exploration and relies more on UCBb later after enough observations have been collected to train the NNs for accurate reward prediction (i.e., reliable exploitation). We prove sub-linear upper bounds on both the cumulative regret and the number of communication rounds of FN-UCB, and empirically demonstrate its competitive performance. © 2023 11th International Conference on Learning Representations, ICLR 2023. All rights reserved.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Mean-field Underdamped Langevin Dynamics and its Spacetime Discretization 41

Mean-field Underdamped Langevin Dynamics and its Spacetime D...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Fu, Qiang Wilson, Ashia Department of Computer Science Yale University New HavenCT United States Department of Electrical Engineering and Computer Science MIT CambridgeMA United States

We propose a new method called the N-particle underdamped Langevin algorithm for optimizing a special class of non-linear functionals defined over the space of probability measures. Examples of problems with this formulation include training mean-field neural networks, maximum mean discrepancy minimization and kernel Stein discrepancy minimization. Our algorithm is based on a novel spacetime discretization of the mean-field underdamped Langevin dynamics, for which we provide a new, fast mixing guarantee. In addition, we demonstrate that our algorithm converges globally in total variation distance, bridging the theoretical gap between the dynamics and its practical implementation. Copyright 2024 by the author(s)

关键词：

来源：评论

学校读者我要写书评

暂无评论

ZEROTH-ORDER OPTIMIZATION WITH TRAJECTORY-INFORMED DERIVATIVE ESTIMATION 11

ZEROTH-ORDER OPTIMIZATION WITH TRAJECTORY-INFORMED DERIVATIV...

引用

11th International Conference on Learning Representations, ICLR 2023

作者： Shu, Yao Dai, Zhongxiang Sng, Weicong Verma, Arun Jaillet, Patrick Low, Bryan Kian Hsiang Dept.of Computer Science National University of Singapore Singapore Dept.of Electrical Engineering and Computer Science MIT United States

Zeroth-order (ZO) optimization, in which the derivative is unavailable, has recently succeeded in many important machine learning *** algorithms rely on finite difference (FD) methods for derivative estimation and gradient descent (GD)-based approaches for ***, these algorithms suffer from query inefficiency because many additional function queries are required for derivative estimation in their every GD update, which typically hinders their deployment in real-world applications where every function query is *** this end, we propose a trajectory-informed derivative estimation method which only employs the optimization trajectory (i.e., the history of function queries during optimization) and hence can eliminate the need for additional function queries to estimate a ***, based on our derivative estimation, we propose the technique of dynamic virtual updates, which allows us to reliably perform multiple steps of GD updates without reapplying derivative *** on these two contributions, we introduce the zeroth-order optimization with trajectory-informed derivative estimation (ZORD) algorithm for query-efficient ZO *** theoretically demonstrate that our trajectory-informed derivative estimation and our ZORD algorithm improve over existing approaches, which is then supported by our real-world experiments such as black-box adversarial attack, non-differentiable metric optimization, and derivative-free reinforcement learning. © 2023 11th International Conference on Learning Representations, ICLR 2023. All rights reserved.

关键词： Trajectories

来源：评论

学校读者我要写书评

暂无评论

Certification with an NP Oracle 14

Certification with an NP Oracle

引用

14th Innovations in Theoretical computer science Conference, ITCS 2023

作者： Blanc, Guy Koch, Caleb Lange, Jane Strassle, Carmen Tan, Li-Yang Department of Computer Science Stanford University CA United States Department of Electrical Engineering and Computer Science MIT CambridgeMA United States

ISBN: (纸本)9783959772631

In the certification problem, the algorithm is given a function f with certificate complexity k and an input x*, and the goal is to find a certificate of size ≤ poly(k) for f's value at x*. This problem is in NPNP, and assuming P ≠ NP, is not in P. Prior works, dating back to Valiant in 1984, have therefore sought to design efficient algorithms by imposing assumptions on f such as monotonicity. Our first result is a BPPNP algorithm for the general problem. The key ingredient is a new notion of the balanced influence of variables, a natural variant of influence that corrects for the bias of the function. Balanced influences can be accurately estimated via uniform generation, and classic BPPNP algorithms are known for the latter task. We then consider certification with stricter instance-wise guarantees: for each x*, find a certificate whose size scales with that of the smallest certificate for x*. In sharp contrast with our first result, we show that this problem is NPNP-hard even to approximate. We obtain an optimal inapproximability ratio, adding to a small handful of problems in the higher levels of the polynomial hierarchy for which optimal inapproximability is known. Our proof involves the novel use of bit-fixing dispersers for gap amplification. © Guy Blanc, Caleb Koch, Jane Lange, Carmen Strassle, and Li-Yang Tan;licensed under Creative Commons License CC-BY 4.0.

关键词： Polynomial approximation

来源：评论

学校读者我要写书评

暂无评论

Incentives in Private Collaborative Machine Learning 37

Incentives in Private Collaborative Machine Learning

引用

37th Conference on Neural Information Processing Systems, NeurIPS 2023

作者： Sim, Rachael Hwee Ling Zhang, Yehong Hoang, Trong Nghia Xu, Xinyi Low, Bryan Kian Hsiang Jaillet, Patrick Department of Computer Science National University of Singapore Singapore Peng Cheng Laboratory China School of Electrical Engineering and Computer Science Washington State University United States Dept. of Electrical Engineering and Computer Science MIT United States

ISBN: (纸本)9781713899921

Collaborative machine learning involves training models on data from multiple parties but must incentivize their participation. Existing data valuation methods fairly value and reward each party based on shared data or model parameters but neglect the privacy risks involved. To address this, we introduce differential privacy (DP) as an incentive. Each party can select its required DP guarantee and perturb its sufficient statistic (SS) accordingly. The mediator values the perturbed SS by the Bayesian surprise it elicits about the model parameters. As our valuation function enforces a privacy-valuation trade-off, parties are deterred from selecting excessive DP guarantees that reduce the utility of the grand coalition's model. Finally, the mediator rewards each party with different posterior samples of the model parameters. Such rewards still satisfy existing incentives like fairness but additionally preserve DP and a high similarity to the grand coalition's posterior. We empirically demonstrate the effectiveness and practicality of our approach on synthetic and real-world datasets. © 2023 Neural information processing systems foundation. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Position: Scarce Resource Allocations That Rely On Machine Learning Should Be Randomized 41

Position: Scarce Resource Allocations That Rely On Machine L...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Jain, Shomik Creel, Kathleen Wilson, Ashia Institute for Data Systems and Society MIT United States Department of Philosophy & Religion Khoury College of Computer Sciences Northeastern University United States Department of Electrical Engineering and Computer Science MIT United States

Contrary to traditional deterministic notions of algorithmic fairness, this paper argues that fairly allocating scarce resources using machine learning often requires randomness. We address why, when, and how to randomize by proposing stochastic procedures that more adequately account for all of the claims that individuals have to allocations of social goods or opportunities. Copyright 2024 by the author(s)

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Leveraging uncertainty quantification in adaptive multiphoton microscopy acquisition

Leveraging uncertainty quantification in adaptive multiphoto...

引用

Computational Optical Imaging and Artificial Intelligence in Biomedical sciences 2024

作者： Ye, Cassandra Tong Han, Jiashu Liu, Kunzan Angelopoulos, Anastasios Griffith, Linda Monakhova, Kristina You, Sixian Department of Electrical Engineering and Computer Science Mit United States Fu Foundation School of Engineering and Applied Science Columbia University United States Department of Eecs University of California Berkeley United States Department of Biological Engineering Mit United States

ISBN: (纸本)9781510669734

Multiphoton microscopy (MPM) provides high-resolution imaging of deep tissue structures while allowing for the visualization of non-labeled biological samples. However, photon generation efficiency of intrinsic biomarkers is low and this, coupled with inherent detection inaccuracies in the photoelectric sensors, leads to an introduction of noise in acquired images. Higher dwelling times can reduce noise but increase the likelihood of photobleaching. To combat this, deep learning methods are being increasingly employed to denoise MPM images, allowing for a more efficient and less invasive process. However, machine learning models can hallucinate information, which is unacceptable for critical scientific microscopy applications. Uncertainty quantification, which has been demonstrated for image-to-image regression tasks, can provide confidence bounds for machine learning-based image reconstruction tasks, adding confidence to predictions. In this work, we discuss incorporating uncertainty quantification into an optimized denoising model to guide adaptive multiphoton microscopy image acquisition. We demonstrate that our method is capable of maintaining fine features in the denoised image, while outperforming other denoising methods by adaptively selecting to reimage the most uncertain pixels in a human endometrium tissue sample. © COPYRIGHT SPIE. Downloading of the abstract is permitted for personal use only.

关键词： Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

没有更多数据了...

全选清除本页清除全部题录导出标记到“检索档案”

共140页 << < 1 2 3 4 5 6 7 8 9 10 > >>

检索报告对象比较合并检索0

隐藏清空

合并搜索

回到顶部

执行限定条件

内容：

评分：

请选择保存的检索档案：

请选择收藏分类：

订阅名称：

通借通还

温馨提示：

图书名称：

借书校区：

取书校区：

手机号码：

邮箱地址：

一卡通帐号：

电话和邮箱必须正确填写，我们会与您联系确认。

联系人：

所在院系：

联系邮箱：

联系电话：

内蒙古自治区呼和浩特市赛罕区大学西街235号邮编: 010021

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：