检索结果-内蒙古大学图书馆

36th Conference on Neural Information Processing Systems, NeurIPS 2022

作者： Luo, Shengjie Li, Shanda Zheng, Shuxin Liu, Tie-Yan Wang, Liwei He, Di National Key Laboratory of General Artificial Intelligence School of Intelligence Science and Technology Peking University China Machine Learning Department School of Computer Science Carnegie Mellon University United States Microsoft Research United States Center for Data Science Peking University China Zhejiang Lab China

ISBN: (纸本)9781713871088

Relative Positional Encoding (RPE), which encodes the relative distance between any pair of tokens, is one of the most successful modifications to the original Transformer. As far as we know, theoretical understanding of the RPE-based Transformers is largely unexplored. In this work, we mathematically analyze the power of RPE-based Transformers regarding whether the model is capable of approximating any continuous sequence-to-sequence functions. One may naturally assume the answer is in the affirmative-RPE-based Transformers are universal function approximators. However, we present a negative result by showing there exist continuous sequence-to-sequence functions that RPE-based Transformers cannot approximate no matter how deep and wide the neural network is. One key reason lies in that most RPEs are placed in the softmax attention that always generates a right stochastic matrix. This restricts the network from capturing positional information in the RPEs and limits its capacity. To overcome the problem and make the model more powerful, we first present sufficient conditions for RPE-based Transformers to achieve universal function approximation. With the theoretical guidance, we develop a novel attention module, called Universal RPE-based (URPE) Attention, which satisfies the conditions. Therefore, the corresponding URPE-based Transformers become universal function approximators. Extensive experiments covering typical architectures and tasks demonstrate that our model is parameter-efficient and can achieve superior performance to strong baselines in a wide range of applications. The code will be made publicly available at https://***/lsj2408/URPE. © 2022 Neural information processing systems foundation. All rights reserved.

关键词： Encoding (symbols)

来源：评论

学校读者我要写书评

暂无评论

Distribution-free binary classification: Prediction sets, confidence intervals and calibration 34

Distribution-free binary classification: Prediction sets, co...

引用

34th Conference on Neural Information Processing Systems, NeurIPS 2020

作者： Gupta, Chirag Podkopaev, Aleksandr Ramdas, Aaditya Machine Learning Department Carnegie Mellon University United States Department of Statistics and Data Science Carnegie Mellon University United States

We study three notions of uncertainty quantification—calibration, confidence intervals and prediction sets—for binary classification in the distribution-free setting, that is without making any distributional assumptions on the data. With a focus towards calibration, we establish a ‘tripod’ of theorems that connect these three notions for score-based classifiers. A direct implication is that distribution-free calibration is only possible, even asymptotically, using a scoring function whose level sets partition the feature space into at most countably many sets. Parametric calibration schemes such as variants of Platt scaling do not satisfy this requirement, while nonparametric schemes based on binning do. To close the loop, we derive distribution-free confidence intervals for binned probabilities for both fixed-width and uniform-mass binning. As a consequence of our ‘tripod’ theorems, these confidence intervals for binned probabilities lead to distribution-free calibration. We also derive extensions to settings with streaming data and covariate shift. © 2020 Neural information processing systems foundation. All rights reserved.

关键词： Calibration

来源：评论

学校读者我要写书评

暂无评论

Personalised Speech-Based PTSD Prediction Using Weighted-Instance learning 46

Personalised Speech-Based PTSD Prediction Using Weighted-Ins...

引用

46th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2024

作者： Kathan, Alexander Amiriparian, Shahin Triantafyllopoulos, Andreas Gebhard, Alexander Milkus, Sabrina Hohmann, Jonas Muderlak, Pauline Schottdorf, Jürgen Musil, Richard Schuller, Björn W. University of Augsburg Eihw - Embedded Intelligence for Healthcare and Wellbeing Germany Mri Technical Univsersity of Munich Chi - Health Informatics Germany Mcml - Munich Center for Machine Learning Germany University Hospital Lmu Munich Department of Psychiatry and Psychotherapy Germany Zentrumspraxis Friedberg Germany Imperial College London Glam - Group on Language Audio & Music United Kingdom Mdsi - Munich Data Science Institute Germany

ISBN: (纸本)9798350371499

Post-traumatic stress disorder (PTSD) is a prevalent disorder that can develop in people who have experienced very stressful, shocking, or distressing events. It has great influence on peoples' daily life and can affect their mental, physical, or social wellbeing, which is why a timely and professional treatment is required. In this paper, we propose a personalised speech-based PTSD prediction approach using a newly collected dataset which consists of 15 participants, including speech recordings from people with PTSD and healthy controls. In addition, the dataset includes data before and after a clinical intervention so that the prediction can be analysed at different points in time. In our experiments, we demonstrate the superiority of the personalised approach, achieving a best area under the ROC curve (AUC) of 82 % and a best relative improvement of 7 % points compared to the non-personalised model. © 2024 IEEE.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

learning Discrete Latent Variable Structures with Tensor Rank Conditions

arXiv

引用

arXiv 2024年

作者： Chen, Zhengming Cai, Ruichu Xie, Feng Qiao, Jie Wu, Anpeng Li, Zijian Hao, Zhifeng Zhang, Kun School of Computer Science Guangdong University of Technology China Machine Learning Department Mohamed bin Zayed University of Artificial Intelligence United Arab Emirates Department of Applied Statistics Beijing Technology and Business University China Department of Computer Science and Technology Zhejiang University China Department of Philosophy Carnegie Mellon University United States

Unobserved discrete data are ubiquitous in many scientific disciplines, and how to learn the causal structure of these latent variables is crucial for uncovering data patterns. Most studies focus on the linear latent variable model or impose strict constraints on latent structures, which fail to address cases in discrete data involving non-linear relationships or complex latent structures. To achieve this, we explore a tensor rank condition on contingency tables for an observed variable set Xp, showing that the rank is determined by the minimum support of a specific conditional set (not necessary in Xp) that d-separates all variables in Xp. By this, one can locate the latent variable through probing the rank on different observed variables set, and further identify the latent causal structure under some structure assumptions. We present the corresponding identification algorithm and conduct simulated experiments to verify the effectiveness of our method. In general, our results elegantly extend the identification boundary for causal discovery with discrete latent variables and expand the application scope of causal discovery with latent variables. Copyright © 2024, The Authors. All rights reserved.

关键词： Tensors

来源：评论

学校读者我要写书评

暂无评论

On conditional versus marginal bias in multi-armed bandits 37

On conditional versus marginal bias in multi-armed bandits

引用

37th International Conference on machine learning, ICML 2020

作者： Shin, Jaehyeok Rinaldo, Alessandro Ramdas, Aaditya Department of Statistics and Data Science Carnegie Mellon University United States Machine Learning Department Carnegie Mellon University United States

ISBN: (纸本)9781713821120

The bias of the sample means of the arms in multiarmed bandits is an important issue in adaptive data analysis that has recently received considerable attention in the literature. Existing results relate in precise ways the sign and magnitude of the bias to various sources of data adaptivity, but do not apply to the conditional inference setting in which the sample means are computed only if some specific conditions are satisfied. In this paper, we characterize the sign of the conditional bias of monotone functions of the rewards, including the sample mean. Our results hold for arbitrary conditioning events and leverage natural monotonicity properties of the data collection policy. We further demonstrate, through several examples from sequential testing and best arm identification, that the sign of the conditional and marginal bias of the sample mean of an arm can be different, depending on the conditioning event. Our analysis offers new and interesting perspectives on the subtleties of assessing the bias in data adaptive settings. © 2020 37th International Conference on machine learning, ICML 2020. 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

Empirical Macroeconomics and DSGE Modeling in Statistical Perspective

arXiv

引用

arXiv 2022年

作者： McDonald, Daniel J. Shalizi, Cosma Rohilla Department of Statistics University of British Columbia VancouverBC Canada Department of Statistics and Data Science and of Machine Learning Carnegie Mellon University PittsburghPA United States Santa Fe Institute Santa FeNM United States

Dynamic stochastic general equilibrium (DSGE) models have been an ubiquitous, and controversial, part of macroeconomics for decades. In this paper, we approach DSGEs purely as statstical models. We do this by applying two common model validation checks to the canonical Smets and Wouters (2007) DSGE: (1) we simulate the model and see how well it can be estimated from its own simulation output, and (2) we see how well it can seem to fit nonsense data. We find that (1) even with centuries' worth of data, the model remains poorly estimated, and (2) when we swap series at random, so that (e.g.) what the model gets as the inflation rate is really hours worked, what it gets as hours worked is really investment, etc., the fit is often only slightly impaired, and in a large percentage of cases actually improves (even out of sample). Taken together, these findings cast serious doubt on the meaningfulness of parameter estimates for this DSGE, and on whether this specification represents anything structural about the economy. Constructively, our approaches can be used for model validation by anyone working with macroeconomic time series. © 2022, CC BY.

关键词： Time series

来源：评论

学校读者我要写书评

暂无评论

Stock Market Forecasting Using LSTM

Stock Market Forecasting Using LSTM

引用

Communication & Computing (WCONF), World Conference on

作者： J. Aswini Dinesh S C. Lakshmipriya Lokesh Krishnaa M Siva Subramanian R Dept of Artificial Intelligence & Machine Learning Saveetha Engineering College(Autonomous) Department of Artificial Intelligence and Data Science Saveetha Engineering College(Autonomous) Department CSE S.A. Engineering College Department CSE R.M.K College of Engineering and Technology

ISBN: (数字)9798350395327

ISBN: (纸本)9798350395334

In this research paper, a novel methodology for forecasting stock market trends is presented: the utilization of Long Short-Term Memory networks, which are a part of RNN network. This model effectively incorporates the delivery of dynamic datasets, model training, and the immediate distribution of the learned TensorFlow model through the utilization of deep learning. The Long Short-Term Memory is a highly effective tool for understanding complex stock market behaviors, as it captures sequential dependencies and effortlessly adapts to changing market conditions. Transparency, collaboration, scalability, user experience, and security are given top priority in the project to guarantee accessibility for users of all levels of expertise. By outperforming conventional neural network architecture in prediction and by capturing dependencies over extended time periods, the LSTM model demonstrates its value. This research may pave the way for additional financial forecasting applications, thereby enhancing the efficacy of decision-making instruments in dynamic stock market environments.

关键词： Deep learning Training Adaptation models Decision making Computer architecture Predictive models User experience Stock markets Forecasting Long short term memory

来源：评论

学校读者我要写书评

暂无评论

Model and Feature Diversity for Bayesian Neural Networks in Mutual learning

arXiv

引用

arXiv 2024年

作者： Pham, Cuong Nguyen, Cuong C. Le, Trung Phung, Dinh Carneiro, Gustavo Do, Thanh-Toan Department of Data Science and AI Monash University Australia Australian Institute for Machine Learning University of Adelaide Australia Centre for Vision Speech and Signal Processing University of Surrey United Kingdom VinAI Viet Nam

Bayesian Neural Networks (BNNs) offer probability distributions for model parameters, enabling uncertainty quantification in predictions. However, they often underperform compared to deterministic neural networks. Utilizing mutual learning can effectively enhance the performance of peer BNNs. In this paper, we propose a novel approach to improve BNNs performance through deep mutual learning. The proposed approaches aim to increase diversity in both network parameter distributions and feature distributions, promoting peer networks to acquire distinct features that capture different characteristics of the input, which enhances the effectiveness of mutual learning. Experimental results demonstrate significant improvements in the classification accuracy, negative log-likelihood, and expected calibration error when compared to traditional mutual learning for BNNs. © 2024, CC BY.

关键词： Probability distributions

来源：评论

学校读者我要写书评

暂无评论

Sampling Strategies for Compressive Imaging Under Statistical Noise

Sampling Strategies for Compressive Imaging Under Statistica...

引用

2023 International Conference on Sampling Theory and Applications, SampTA 2023

作者： Hoppe, Frederik Krahmer, Felix Verdun, Claudio Mayrink Menzel, Marion I. Rauhut, Holger Rwth Aachen University Chair of Mathematics of Information Processing Aachen Germany Technical University of Munich Department of Mathematics Munich Germany Munich Center for Machine Learning Munich Germany Technical University of Munich Munich Data Science Institute Germany Technische Hochschule Ingolstadt AImotion Bavaria Ingolstadt Germany Technical University of Munich Department of Physics Garching Germany Ge Healthcare Munich Germany

ISBN: (纸本)9798350328851

Most of the compressive sensing literature in signal processing assumes that the noise present in the measurement has an adversarial nature, i.e., it is bounded in a certain norm. At the same time, the randomization introduced in the sampling scheme usually assumes an i.i.d. model where rows are sampled with replacement. In this case, if a sample is measured a second time, it does not add additional information. For many applications, where the statistical noise model is a more accurate one, this is not true anymore since a second noisy sample comes with an independent realization of the noise, so there is a fundamental difference between sampling with and without replacement. Therefore, a more careful analysis must be performed. In this short note, we illustrate how one can mathematically transition between these two noise models. This transition gives rise to a weighted LASSO reconstruction method for sampling without replacement, which numerically improves the solution of high-dimensional compressive imaging problems. © 2023 IEEE.

关键词： Compressed sensing

来源：评论

学校读者我要写书评

暂无评论

Regularized Shannon sampling formulas related to the special affine Fourier transform

arXiv

引用

arXiv 2023年

作者： Filbir, Frank Tasche, Manfred Veselovska, Anna Institute of Mathematics University of Rostock Germany Department of Mathematics Munich Data Science Institute Technical University of Munich Munich Center for Machine Learning Garching/Munich Germany

In this paper, we present new regularized Shannon sampling formulas related to the special affine Fourier transform (SAFT). These sampling formulas use localized sampling with special compactly supported window functions, namely B-spline, sinh-type, and continuous Kaiser–Bessel window functions. In contrast to the Shannon sampling series for SAFT, the regularized Shannon sampling formulas for SAFT possesses an exponential decay of the approximation error and are numerically robust in the presence of noise, if certain oversampling condition is fulfilled. Several numerical experiments illustrate the theoretical *** Codes 94A20, 42A38, 65T50 © 2023, CC BY.

关键词： Fourier transforms

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：