检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Treger, Shify Ullman, Shimon Department of Computer Science and Applied Mathematics Weizmann Institute of Science

Early in development, infants learn a range of useful concepts, which can be challenging from a computational standpoint. This early learning comes together with an initial understanding of aspects of the meaning of concepts, e.g., their implications, causality, and using them to predict likely future events. All this is accomplished in many cases with little or no supervision, and from relatively few examples, compared with current network models. In learning about objects and human-object interactions, early acquired and possibly innate concepts are often used in the process of learning additional, more complex concepts. In the current work, we model how early-acquired concepts are used in the learning of subsequent concepts, and compare the results with standard deep network modeling. We focused in particular on the use of the concepts of animacy and goal attribution in learning to predict future events. We show that the use of early concepts in the learning of new concepts leads to better learning (higher accuracy) and more efficient learning (requiring less data). We further show that this integration of early and new concepts shapes the representation of the concepts acquired by the model. The results show that when the concepts were learned in a human-like manner, the emerging representation was more useful, as measured in terms of generalization to novel data and tasks. On a more general level, the results suggest that there are likely to be basic differences in the conceptual structures acquired by current network models compared to human learning. © 2025, CC BY.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

FreqRISE: Explaining time series using frequency masking 6

FreqRISE: Explaining time series using frequency masking

引用

6th Northern Lights Deep Learning Conference, NLDL 2025

作者： Brüsch, Thea Wickstrøm, Kristoffer Knutsen Schmidt, Mikkel N. Alstrøm, Tommy Sonne Jenssen, Robert Department of Applied Mathematics and Computer Science Technical University of Denmark Denmark Department of Physics and Technology UiT The Arctic University of Norway Norway Norwegian Computing Center Oslo Norway

Time series data is fundamentally important for many critical domains such as healthcare, finance, and climate, where explainable models are necessary for safe automated decision-making. To develop explainable artificial intelligence in these domains therefore implies explaining salient information in the time series. Current methods for obtaining saliency maps assumes localized information in the raw input space. In this paper, we argue that the salient information of a number of time series is more likely to be localized in the frequency domain. We propose FreqRISE, which uses masking-based methods to produce explanations in the frequency and time-frequency domain, and outperforms strong baselines across a number of tasks. The source code is available here: https://***/theabrusch/FreqRISE. © NLDL *** rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Multi-Level Feature Distillation of Joint Teachers Trained on Distinct Image Datasets

Multi-Level Feature Distillation of Joint Teachers Trained o...

引用

2025 IEEE/CVF Winter Conference on Applications of computer Vision, WACV 2025

作者： Iordache, Adrian Alexe, Bogdan Ionescu, Radu Tudor University of Bucharest Department of Computer Science Bucharest Romania 'Gheorghe Mihoc - Caius Iacob' Institute of Mathematical Statistics and Applied Mathematics The Romanian Academy Bucharest Romania

ISBN: (纸本)9798331510831

We propose a novel teacher-student framework to distill knowledge from multiple teachers trained on distinct datasets. Each teacher is first trained from scratch on its own dataset. Then, the teachers are combined into a joint architecture, which fuses the features of all teachers at multiple representation levels. The joint teacher architecture is fine-tuned on samples from all datasets, thus gathering useful generic information from all data samples. Finally, we employ a multi-level feature distillation procedure to transfer the knowledge to a student model for each of the considered datasets. We conduct image classification experiments on seven benchmarks, and action recognition experiments on three benchmarks. To illustrate the power of our feature distillation procedure, the student architectures are chosen to be identical to those of the individual teachers. To demonstrate the flexibility of our approach, we combine teachers with distinct architectures. We show that our novel Multi-Level Feature Distillation (MLFD) can significantly surpass equivalent architectures that are either trained on individual datasets, or jointly trained on all datasets at once. Furthermore, we confirm that each step of the proposed training procedure is well motivated by a comprehensive ablation study. We publicly release our code at https://***/AdrianIordache/MLFD. © 2025 IEEE.

关键词： Teaching

来源：评论

学校读者我要写书评

暂无评论

Thermal-Aware Communication

引用

IEEE Transactions on Information Theory 2025年第6期71卷 4145-4155页

作者： Chee, Yeow Meng Etzion, Tuvi Immink, Kees A. Schouhamer Nguyen, Tuan Thanh Vu, Van Khu Weber, Jos H. Yaakobi, Eitan Singapore University of Technology and Design Singapore Technion — Israel Institute of Technology Department of Computer Science Haifa3200003 Israel National University of Singapore Department of Industrial Systems Engineering and Management Singapore Turing Machines Inc Rotterdam3016 DK Netherlands Singapore University of Technology and Design Science Mathematics and Technology Cluster 487372 Singapore Delft University of Technology Department of Applied Mathematics Delft2628 CD Netherlands

Temperature control is of utmost importance in transmission systems. In this paper, a binary channel model is considered in which the transmission of a one causes a temperature increase while communicating a zero causes a temperature drop. By putting constraints on the input sequences, it is guaranteed that the channel temperature will not exceed a certain pre-determined maximum. In the asymptotic regime, the capacity of such a channel is studied. For the non-asymptotic regime, fixed-length codes are presented, with the property that codewords can be freely cascaded without violating the temperature constraint. Optimization of the code size is investigated and codewords are enumerated using generating functions. © 1963-2012 IEEE.

关键词： Channel capacity

来源：评论

学校读者我要写书评

暂无评论

THE INCLUSION-EXCLUSION PRINCIPLE AND RECURRENCES FOR PARTITION NUMBERS

引用

UPB Scientific Bulletin, Series A: applied mathematics and Physics 2025年第1期87卷 97-106页

作者： Ballantine, Cristina Merca, Mircea Department of Mathematics and Computer Science College of The Holy Cross WorcesterMA01610 United States Department of Mathematical Methods and Models Fundamental Sciences Applied in Engineering Research Center National University of Science and Technology Politehnica Bucharest BucharestRO-060042 Romania Academy of Romanian Scientists BucharestRO-050044 Romania

The inclusion-exclusion principle together with Legendre type theorems for number of distinct restricted partitions weighted by the parity of their length are used to give several recurrence relations for restricted partition numbers as well as for overpartition numbers. In the case of overpartitions, POD partitions and 3-color partitions, we give combinatorial proofs for the Legendre type theorems and arrive to combinatorial proofs for the recurrence relations. © 2025, Politechnica University of Bucharest. All rights reserved.

关键词： Combinatorial mathematics

来源：评论

学校读者我要写书评

暂无评论

Latent Representation Learning for Multimodal Brain Activity Translation

Latent Representation Learning for Multimodal Brain Activity...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Afrasiyabi, Arman Bhaskar, Dhananjay Busch, Erica L. Caplette, Laurent Singh, Rahul Lajoie, Guillaume Turk-Browne, Nicholas B. Krishnaswamy, Smita Department of Computer Science Department of Applied Mathematics Department of Psychology Department of Genetics Department of Mathematics and Statistics Mila - Quebec AI Institute Canada Université de Montréal Canada Wu Tsai Institute United States Yale University United States

ISBN: (纸本)9798350368741

Neuroscience employs diverse neuroimaging techniques, each offering distinct insights into brain activity, from electrophysiological recordings such as EEG, which have high temporal resolution, to hemodynamic modalities such as fMRI, which have increased spatial precision. However, integrating these heterogeneous data sources remains a challenge, which limits a comprehensive understanding of brain function. We present the Spatiotemporal Alignment of Multimodal Brain Activity (SAMBA) framework, which bridges the spatial and temporal resolution gaps across modalities by learning a unified latent space free of modality-specific biases. SAMBA introduces a novel attention-based wavelet decomposition for spectral filtering of electrophysiological recordings, graph attention networks to model functional connectivity between functional brain units, and recurrent layers to capture temporal autocorrelations in brain signal. We show that the training of SAMBA, aside from achieving translation, also learns a rich representation of brain information processing. We showcase this classify external stimuli driving brain activity from the representation learned in hidden layers of SAMBA, paving the way for broad downstream applications in neuroscience research and clinical contexts. © 2025 IEEE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Sampling List Packings 16

Sampling List Packings

引用

16th Innovations in Theoretical computer science Conference, ITCS 2025

作者： Camrud, Evan Davies, Ewan Karduna, Alex Lee, Holden Department of Mathematics and Statistics Middlebury College VT United States Department of Computer Science Colorado State University Fort CollinsCO United States Department of Applied Mathematics and Statistics Johns Hopkins University BaltimoreMD United States

ISBN: (纸本)9783959773614

We initiate the study of approximately counting the number of list packings of a graph. The analogous problem for usual vertex coloring and list coloring has attracted substantial attention. For list packing the setup is similar, but we seek a full decomposition of the lists of colors into pairwise-disjoint proper list colorings. The existence of a list packing implies the existence of a list coloring, but the converse is false. Recent works on list packing have focused on existence or extremal results of on the number of list packings, but here we turn to the algorithmic aspects of counting and sampling. In graphs of maximum degree ∆ and when the number of colors is at least Ω(∆2), we give a fully polynomial-time randomized approximation scheme (FPRAS) based on rapid mixing of a natural Markov chain (the Glauber dynamics) which we analyze with the path coupling technique. Some motivation for our work is the investigation of an atypical spin system, one where the number of spins for each vertex is much larger than the graph degree. © Evan Camrud, Ewan Davies, Alex Karduna, and Holden Lee.

关键词： Markov chains

来源：评论

学校读者我要写书评

暂无评论

Modulation of blood pressure by dietary potassium and sodium: sex differences and modeling analysis

引用

American Journal of Physiology - Renal Physiology 2025年第3期328卷 F406-F417页

作者： Stadt, Melissa Layton, Anita T. Department of Applied Mathematics University of Waterloo Waterloo ON Canada Department of Biology University of Waterloo Waterloo ON Canada Cheriton School of Computer Science University of Waterloo Waterloo ON Canada School of Pharmacy University of Waterloo Waterloo ON Canada

High Naþ intake has been linked to elevations in blood pressure, whereas Kþ has the opposite effect. The underlying mechanisms involve complex interactions among renal function, fluid volume, fluid-regulator... 详细信息

High Na^þ intake has been linked to elevations in blood pressure, whereas K^þ has the opposite effect. The underlying mechanisms involve complex interactions among renal function, fluid volume, fluid-regulatory hormones, vasculature, cardiac function, and the autonomic nervous system. These mechanisms are likely modulated by sex, given the known sex differences in blood pressure regulation and the higher prevalence of hypertension in men. The source of these observed sex differences may be traced to organ and tissue levels, given that kidney function, intrarenal renin-angiotensin system components, renal sympathetic nervous activity, and nitric oxide bioavailability all exhibit sex differences. To assess the functional impact of each of these sex differences, we developed sex-specific computational models to simulate whole-body Na^þ, K^þ, and fluid homeostasis, and the effects on blood pressure. The models describe the interactions among the renal system, cardiovascular system, gastrointestinal system, renal sympathetic nervous system, and renin-angiotensin-aldosterone system. Model simulations suggest that women’s attenuated blood pressure response to hypertensive stimuli, including high Na^þ intake, may be largely attributable to the female renal transporter abundance pattern. In addition, we investigated the causal link between high K^þ intake and blood pressure reduction. The models simulate renal response to high K^þ intake, including the immediate gastrointestinal feedforward signals to the kidneys to increase K^þ excretion, and the longer-term response to decrease proximal fractional Na^þ reabsorption and distal K^þ reabsorption. With these assumptions, simulations of high K^þ intake yielded kaliuresis, natriuresis, and a substantial reduction in blood pressure, even when combined with high Na^þ intake. Copyright © 2025 the American Physiolo

关键词： blood pressure potassium handling sex differences sodium handling

来源：评论

学校读者我要写书评

暂无评论

Data-Driven Bandwidth Selection in Kernel Density Estimation via Unsupervised Learning 8th

Data-Driven Bandwidth Selection in Kernel Density Estimatio...

引用

8th International Symposium on Modelling and Implementation of Complex Systems, MISC 2024

作者： Guidoum, Arsalane Chouaib Henider, Amel Department of Mathematics and Computer Science Faculty of Sciences and Technology University of Tamanghasset Tamanghasset11000 Algeria Department of Finance and Actuarial National Higher School of Statistics and Applied Economics Kolea42003 Algeria

ISBN: (纸本)9783031821110

The selection of optimal bandwidth bw in Kernel Density Estimation (KDE) is crucial for accurate density estimation. Traditional methods, such as unbiased and biased cross-validation and their variants, often suffer from performance and computational limitations. This study presents a novel, data-driven approach to bandwidth selection using unsupervised machine learning techniques. Synthetic samples are generated from the original data, a comprehensive set of statistical parameters is calculated, and bandwidth is estimated using a rule-of-thumb [2]. Feature importance is assessed through random forests (RF) to identify the most influential factors in bandwidth selection. Various unsupervised learning models are then applied to predict the optimal bandwidth for the original sample bwos. The results demonstrate that this machine learning-based approach achieves superior accuracy and computational efficiency compared to traditional cross-validation methods. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Cubature Kalman Fusion Filtering Under Amplify-and-Forward Relays With Randomly Varying Channel Parameters

引用

IEEE/CAA Journal of Automatica Sinica 2025年第2期12卷 356-368页

作者： Jiaxing Li Zidong Wang Jun Hu Hongli Dong Hongjian Liu the Department of Applied Mathematics Harbin University of Science and Technology IEEE the Department of Computer Science Brunel University London the School of Automation Harbin University of Science and Technology the Artificial Intelligence Energy Research Institute Northeast Petroleum University the Heilongjiang Provincial Key Laboratory of Networking and Intelligent Control Northeast Petroleum University the National Key Laboratory of Continental Shale Oil of China Northeast Petroleum University the Key Laboratory of Advanced Perception and Intelligent Control of High-End Equipment Ministry of Education Anhui Polytechnic University the School of Mathematics and Physics Anhui Polytechnic University

In this paper, the problem of cubature Kalman fusion filtering(CKFF) is addressed for multi-sensor systems under amplify-and-forward(AaF) relays. For the purpose of facilitating data transmission, AaF relays are utilized to regulate signal communication between sensors and filters. Here, the randomly varying channel parameters are represented by a set of stochastic variables whose occurring probabilities are permitted to exhibit bounded uncertainty. Employing the spherical-radial cubature principle, a local filter under AaF relays is initially constructed. This construction ensures and minimizes an upper bound of the filtering error covariance by designing an appropriate filter gain. Subsequently, the local filters are fused through the application of the covariance intersection fusion rule. Furthermore, the uniform boundedness of the filtering error covariance's upper bound is investigated through establishing certain sufficient conditions. The effectiveness of the proposed CKFF scheme is ultimately validated via a simulation experiment concentrating on a three-phase induction machine.

关键词： Amplify-and-forward (AaF) relays covariance intersection fusion cubature Kalman filtering multi-sensor systems uniform boundedness

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：