检索结果-内蒙古大学图书馆

An automatic analysis of ultrasound vocalisations for the prediction of interaction context in captive Egyptian fruit bats

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Triantafyllopoulos, Andreas Gebhard, Alexander Milling, Manuel Rampp, Simon Schuller, Björn Technical University of Munich MRI Munich Germany EIHW - Embedded Intelligence for Health Care and Wellbeing Augsburg Germany MCML - Munich Center for Machine Learning Munich Germany MDSI - Munich Data Science Institute Munich Germany GLAM - Group on Language Audio & Music Imperial College London United Kingdom

Prior work in computational bioacoustics has mostly focused on the detection of animal presence in a particular habitat. However, animal sounds contain much richer information than mere presence;among others, they encapsulate the interactions of those animals with other members of their species. Studying these interactions is almost impossible in a naturalistic setting, as the ground truth is often lacking. The use of animals in captivity instead offers a viable alternative pathway. However, most prior works follow a traditional, statistics-based approach to analysing interactions. In the present work, we go beyond this standard framework by attempting to predict the underlying context in interactions between captive Rousettus Aegyptiacus using deep neural networks. We reach an unweighted average recall of over 30% - more than thrice the chance level - and show error patterns that differ from our statistical analysis. This work thus represents an important step towards the automatic analysis of states in animals from sound. © 2024, CC BY-NC-ND.

关键词： Animals

Comparing Sequential Forecasters

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Choe, Yo Joong Ramdas, Aaditya Data Science Institute University of Chicago United States Department of Statistics and Data Science Machine Learning Department Carnegie Mellon University United States

Consider two forecasters, each making a single prediction for a sequence of events over time. We ask a relatively basic question: how might we compare these forecasters, either online or post-hoc, while avoiding unverifiable assumptions on how the forecasts and outcomes were generated? In this paper, we present a rigorous answer to this question by designing novel sequential inference procedures for estimating the time-varying difference in forecast scores. To do this, we employ confidence sequences (CS), which are sequences of confidence intervals that can be continuously monitored and are valid at arbitrary data-dependent stopping times ("anytime-valid"). The widths of our CSs are adaptive to the underlying variance of the score differences. Underlying their construction is a game-theoretic statistical framework, in which we further identify e-processes and p-processes for sequentially testing a weak null hypothesis — whether one forecaster outperforms another on average (rather than always). Our methods do not make distributional assumptions on the forecasts or outcomes;our main theorems apply to any bounded scores, and we later provide alternative methods for unbounded scores. We empirically validate our approaches by comparing real-world baseball and weather forecasters. © 2021, CC BY.

关键词： Baseball

An iterative-based difference scheme for nonlinear fractional integro-differential equations of Volterra type

学校读者我要写书评

暂无评论

Partial Differential Equations in Applied Mathematics 2025年 13卷

作者： Saini, Gaurav Ghosh, Bappa Chand, Sunita Mohapatra, Jugal Center for Data Science Department of Computer Science and Engineering Siksha ‘O’ Anusandhan (Deemed to be University) India Center for Artificial Intelligence and Machine Learning Department of Computer Science and Engineering Siksha ‘O’ Anusandhan (Deemed to be University) India Department of Mathematics Siksha ‘O’ Anusandhan (Deemed to be University) India Department of Mathematics National Institute of Technology Rourkela India

This paper presents an iterative difference scheme for solving nonlinear fractional integro-differential equations of Volterra type, which are widely used in modeling memory-dependent phenomena in various scientific and engineering applications. The scheme employs Caputo's fractional derivative to handle the non-local nature of the fractional derivative and introduces an iterative approach to enhance accuracy and stability. By discretizing the domain of interest on a uniform mesh and the present non-local differential operator using a well-established L1 technique, we derive a nonlinear difference equation that captures the essential dynamics of the underlying continuous problem. The corresponding nonlinear equation is solved by employing the Daftardar-Gejji and Jafari (DGJ) method. The convergence and stability of the proposed scheme are rigorously analyzed under sufficiently smooth initial data, and the method produces reliable numerical solutions. Numerical experiments are conducted to validate the effectiveness of the scheme, demonstrating its efficiency. © 2025 The Authors

关键词： Composite trapezoidal formula Error estimation L1 technique Nonlinear integro-differential equations

Big data in Social Media: Analyzing Trends, Patterns and Challenges 2

学校读者我要写书评

暂无评论

Big Data in Social Media: Analyzing Trends, Patterns and Cha...

2nd International Conference on machine learning and Autonomous Systems, ICMLAS 2025

作者： Jikar, Nayan Tale, Yash Tale, Abhay Barhate, Aditya Verma, Prateek Jikar, Aman Datta Meghe Institute of Higher Education and Research Sawangi Faculty of Engineering and Technology Department of Artificial Intelligence and Machine Learning Maharashtra Wardha442001 India Datta Meghe Institute of Higher Education and Research Sawangi Faculty of Engineering and Technology Department of Artificial Intelligence and Data Science Maharashtra Wardha442001 India Datta Meghe Institute of Higher Education and Research Faculty of Engineering and Technology Department of Computer Science and Engineering Maharashtra Wardha442001 India

ISBN: (纸本)9798331505745

The huge volumes of data produced in social media provide both new possibilities and challenges to analytics. The present paper emphasizes Big data analytics and machine learning (ML) methods to uncover trends, patterns, and user behavior from social media-related data. Such vital concepts, like the 'Four Vs' of Big data: Volume, Velocity, Variety, and Veracity, and innovative tools for datacollection, storage, and preprocessing are covered here as well. Sentiment analysis, trend forecasting, and user behaviormodeling are some of the examples of what is possible using ML and Artificial Intelligence (AI) for deriving actionable insights. Marketing campaigns, crisis communications, and political campaigns are some of the scenarios that are covered to bring out real world applications of such technologies, along with their transformative effects. Lastly, data privacy, quality, and scalability issues are noted, along with ethical concerns and biases. Directions for the future point to developments in real-time data analysis, anonymization, and the changing role of AI in social media platforms. This research emphasizes the significance of Big data and machine learning in driving innovation and decision-making in the digital era. © 2025 IEEE.

关键词： Tweets

Thermal disorder and phonon softening in the ferroelectric phase transition of lead titanate

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Xie, Pinchen Chen, Yixiao Weinan, E. Car, Roberto Program in Applied and Computational Mathematics Princeton University PrincetonNJ08544 United States AI for Science Institute Beijing China Center for Machine Learning Research School of Mathematical Sciences Peking University Beijing China Department of Chemistry Department of Physics Program in Applied and Computational Mathematics Princeton Materials Institute Princeton University PrincetonNJ08544 United States

We report an extensive molecular dynamics study of ab-initio quality of the ferroelectric phase transition in crystalline PbTiO3. We model anharmonicity accurately in terms of potential energy and polarization surfaces trained on density functional theory data with modern machine learning techniques. Our simulations demonstrate that the transition has a strong order-disorder character, in agreement with diffraction experiments, and provide fresh insight into the approach to equilibrium upon crossing the transition temperature. We find that the macroscopic polarization appears/disappears due to dipolar switching at the nanometer scale. We also compute the infrared optical absorption spectra in both the ferroelectric and the paraelectric phases, finding good agreement with the experimental Raman frequencies. For a long time, the almost ideal displacive character of the soft mode detected by Raman scattering in the paraelectric phase has been contrasted with the order-disorder character of the transition suggested by diffraction. We settle this issue by showing that the soft mode coexists with a strong Debye relaxation due to the thermal disordering of the dipoles. The Debye relaxation feature is centered at zero frequency and appears near the transition temperature in both the ferroelectric and the paraelectric phases. © 2024, CC BY.

关键词： Ferroelectricity

Probabilistic task modelling for meta-learning

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Nguyen, Cuong Do, Thanh-Toan Carneiro, Gustavo Australian Institute for Machine Learning University of Adelaide Australia Department of Data Science and AI Monash University Australia

We propose probabilistic task modelling - a generative probabilistic model for collections of tasks used in meta-learning. The proposed model combines variational auto-encoding and latent Dirichlet allocation to model each task as a mixture of Gaussian distribution in an embedding space. Such modelling provides an explicit representation of a task through its task-theme mixture. We present an efficient approximation inference technique based on variational inference method for empirical Bayes parameter estimation. We perform empirical evaluations to validate the task uncertainty and task distance produced by the proposed method through correlation diagrams of the prediction accuracy on testing tasks. We also carry out experiments of task selection in meta-learning to demonstrate how the task relatedness inferred from the proposed model help to facilitate meta-learning algorithms. © 2021, CC BY.

关键词： Mixtures

machine learning-Based Security for Cloud Computing Challenges and Implications

学校读者我要写书评

暂无评论

Machine Learning-Based Security for Cloud Computing Challeng...

North Karnataka Subsection Flagship International Conference (NKCon), IEEE

作者： Rahul Dattangire Rushikesh Burle Divya Biradar Leelkanth Dewangan Independent Researcher Data Engineering Houston Texas USA Artificial Intelligence and Machine Learning Faculty of Engineering and Technology Datta Meghe Institute of Higher Education and Research Wardha Maharashtra India Computer Science University of Texas at Arlington Arlington Texas USA G H Raisoni College of Engineering Nagpur Maharashtra India

ISBN: (数字)9798350364569

ISBN: (纸本)9798350364576

Cloud computing" is a computer model that provides end users with quantifiable, scalable, and on-demand services. These days, almost every organization uses computer technology extensively for infrastructure, cost-cutting, advanced platforms, data processing, data analytics, and other uses. End users can use any online application from anywhere to access the cloud service providers' (CSP) services. It is imperative to guarantee the security of cloud infrastructure, and a multitude of research employing various technologies is used to provide more accurate and potent defenses against cloud threats. machine learning has shown to be a more useful technology in recent years for protecting cloud infrastructures. machine learning algorithms are trained to generate models that mechanize the process of recognizing cloud threats more precisely than any other technology by using a range of actual datasets as training grounds. A couple of the most recent research that has worked on machine learning to defend against cloud attacks are examined in this paper.

关键词： Training Cloud computing machine learning algorithms data analysis Accuracy Computational modeling Reinforcement learning Organizations Computer security

The Implicit Bias of Batch Normalization in Linear Models and Two-layer Linear Convolutional Neural Networks

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Cao, Yuan Zou, Difan Li, Yuanzhi Gu, Quanquan Department of Statistics and Actuarial Science Department of Mathematics The University of Hong Kong Hong Kong Department of Computer Science Institute of Data Science The University of Hong Kong Hong Kong Machine Learning Department Carnegie Mellon University PittsburghPA United States Department of Computer Science University of California Los AngelesCA United States

We study the implicit bias of batch normalization trained by gradient descent. We show that when learning a linear model with batch normalization for binary classification, gradient descent converges to a uniform margin classifier on the training data with an exp(−Ω(log2 t)) convergence rate. This distinguishes linear models with batch normalization from those without batch normalization in terms of both the type of implicit bias and the convergence rate. We further extend our result to a class of two-layer, single-filter linear convolutional neural networks, and show that batch normalization has an implicit bias towards a patch-wise uniform margin. Based on two examples, we demonstrate that patch-wise uniform margin classifiers can outperform the maximum margin classifiers in certain learning problems. Our results contribute to a better theoretical understanding of batch normalization. © 2023, CC BY-SA.

关键词： Convolution

The Benefits of Mixup for Feature learning

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Zou, Difan Cao, Yuan Li, Yuanzhi Gu, Quanquan Department of Computer Science Institute of Data Science The University of Hong Kong Hong Kong Department of Statistics and Actuarial Science Department of Mathematics The University of Hong Kong Hong Kong Machine Learning Department Carnegie Mellon University PittsburghPA United States Department of Computer Science University of California Los AngelesCA United States

Mixup, a simple data augmentation method that randomly mixes two data points via linear interpolation, has been extensively applied in various deep learning applications to gain better generalization. However, the theoretical underpinnings of its efficacy are not yet fully understood. In this paper, we aim to seek a fundamental understanding of the benefits of Mixup. We first show that Mixup using different linear interpolation parameters for features and labels can still achieve similar performance to the standard Mixup. This indicates that the intuitive linearity explanation in Zhang et al. (2018) may not fully explain the success of Mixup. Then we perform a theoretical study of Mixup from the feature learning perspective. We consider a feature-noise data model and show that Mixup training can effectively learn the rare features (appearing in a small fraction of data) from its mixture with the common features (appearing in a large fraction of data). In contrast, standard training can only learn the common features but fails to learn the rare features, thus suffering from bad generalization performance. Moreover, our theoretical analysis also shows that the benefits of Mixup for feature learning are mostly gained in the early training phase, based on which we propose to apply early stopping in Mixup. Experimental results verify our theoretical findings and demonstrate the effectiveness of the early-stopped Mixup training. © 2023, CC BY-SA.

关键词： Deep learning