检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Wegner, Anatol E. Olhede, Sofia C. Machine Learning for Complex Networks Center for Artificial Intelligence and Data Science University of Würzburg Würzburg97070 Germany Institute of Mathematics École Polytechnique Fédérale de Lausanne Lausanne1015 Switzerland

We propose a method for obtaining parsimonious decompositions of networks into higher order interactions which can take the form of arbitrary motifs. The method is based on a class of analytically solvable generative models, where vertices are connected via explicit copies of motifs, which in combination with non-parametric priors allow us to infer higher order interactions from dyadic graph data without any prior knowledge on the types or frequencies of such interactions. Crucially, we also consider’degree–corrected’ models that correctly reflect the degree distribution of the network and consequently prove to be a better fit for many real world–networks compared to non-degree corrected models. We test the presented approach on simulated data for which we recover the set of underlying higher order interactions to a high degree of accuracy. For empirical networks the method identifies concise sets of atomic subgraphs from within thousands of candidates that cover a large fraction of edges and include higher order interactions of known structural and functional significance. The method not only produces an explicit higher order representation of the network but also a fit of the network to analytically tractable models opening new avenues for the systematic study of higher order network structures. Copyright © 2024, The Authors. 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

Diversity Seeking Techniques for Red-Teaming Large Language Models

Diversity Seeking Techniques for Red-Teaming Large Language ...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Seokhan Lee Bonhwa Ku Hanseok Ko Dept. Computer Science and Engineering Korea University Seoul Republic of Korea Machine Learning Big Data Institute Korea University Seoul Republic of Korea Dept. Electrical and Computer Engineering Korea University Seoul Republic of Korea

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

In this paper, we present new techniques for increasing the diversity of red-teaming prompts generated by automated machine learning-based methods, thereby enabling the discovery of more vulnerabilities in large language models. Using reinforcement learning to train models to output effective prompts for this task results in the models converging deterministically to a single output. Our first technique, which we term Defender, acts by blocking the reward signal for prompts that have already been discovered, thus making what was a stationary problem into a non-stationary problem that compels the reward maximizing algorithm to continually seek new prompts. Our second technique, Teamplay, trains two prompt generation models in tandem and adds the KL divergence between them to the reward in order to make them search in disparate regions of the space of prompts. Our techniques are shown experimentally to increase the effectiveness and diversity of prompts generated by existing reinforcement learning baselines.

关键词： learning systems Large language models Diversity reception Signal processing algorithms Reinforcement learning Signal processing Acoustics Safety Speech processing

来源：评论

学校读者我要写书评

暂无评论

Identifying General Mechanism Shifts in Linear Causal Representations

arXiv

引用

arXiv 2024年

作者： Chen, Tianyu Bello, Kevin Locatello, Francesco Aragam, Bryon Ravikumar, Pradeep Department of Statistics and Data Sciences University of Texas Austin United States Booth School of Business University of Chicago United States Machine Learning Department Carnegie Mellon University United States Institute of Science and Technology Austria

We consider the linear causal representation learning setting where we observe a linear mixing of d unknown latent factors, which follow a linear structural causal model. Recent work has shown that it is possible to recover the latent factors as well as the underlying structural causal model over them, up to permutation and scaling, provided that we have at least d environments, each of which corresponds to perfect interventions on a single latent node (factor). After this powerful result, a key open problem faced by the community has been to relax these conditions: allow for coarser than perfect single-node interventions, and allow for fewer than d of them, since the number of latent factors d could be very large. In this work, we consider precisely such a setting, where we allow a smaller than d number of environments, and also allow for very coarse interventions that can very coarsely change the entire causal graph over the latent factors. On the flip side, we relax what we wish to extract to simply the list of nodes that have shifted between one or more environments. We provide a surprising identifiability result that it is indeed possible, under some very mild standard assumptions, to identify the set of shifted nodes. Our identifiability proof moreover is a constructive one: we explicitly provide necessary and sufficient conditions for a node to be a shifted node, and show that we can check these conditions given observed data. Our algorithm lends itself very naturally to the sample setting where instead of just interventional distributions, we are provided datasets of samples from each of these distributions. We corroborate our results on both synthetic experiments as well as an interesting psychometric dataset. The code can be found at https://***/TianyuCodings/iLCS. © 2024, CC BY.

关键词：

来源：评论

学校读者我要写书评

暂无评论

On convergence of federated averaging langevin dynamics 24

On convergence of federated averaging langevin dynamics

引用

Proceedings of the Fortieth Conference on Uncertainty in Artificial Intelligence

作者： Wei Deng Qian Zhang Yi-An Ma Zhao Song Guang Lin Machine Learning Research Morgan Stanley Department of Statistics Purdue University West Lafayette Halicioglu Data Science Institute University of California San Diego Adobe Research Department of Mathematics and School of Mechanical Engineering Purdue University

We propose a federated averaging Langevin algorithm (FA-LD) for uncertainty quantification and mean predictions with distributed clients. In particular, we generalize beyond normal posterior distributions and consider a general class of models. We develop theoretical guarantees for FA-LD for strongly log-concave distributions with non-i.i.d data and study how the injected noise and the stochastic-gradient noise, the heterogeneity of data, and the varying learning rates affect the convergence. Such an analysis sheds light on the optimal choice of local updates to minimize the communication cost. Important to our approach is that the communication efficiency does not deteriorate with the injected noise in the Langevin algorithms. In addition, we examine in our FA-LD algorithm both independent and correlated noise used over different clients. We observe that there is a tradeoff between the pairs among communication, accuracy, and data privacy. As local devices may become inactive in federated networks, we also show convergence results based on different averaging schemes where only partial device updates are available. In such a case, we discover an additional bias that does not decay to zero.

关键词：

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 23

Model and feature diversity for bayesian neural networks in ...

引用

Proceedings of the 37th International Conference on Neural Information Processing Systems

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

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.

关键词：

来源：评论

学校读者我要写书评

暂无评论

HealthGuardian: Artificial Intelligence System for Early Diagnosis and Clinical Support

HealthGuardian: Artificial Intelligence System for Early Dia...

引用

International Conference on Computer and Communications Technologies (ICCCT)

作者： V Radhamani D. Sudha Devi E Chandra Blessie P J Isabella Priya R Tanushree Department of Computing (Decision and Computing Sciences) Coimbatore Institute of Technology Coimbatore Tamil Nadu India Department of Computing (Data Science) Coimbatore Institute of Technology Coimbatore Tamil Nadu India Department of Computing (Artificial Intelligence and Machine Learning) Coimbatore Institute of Technology Coimbatore Tamil Nadu India

ISBN: (数字)9798331537579

ISBN: (纸本)9798331537586

In today's fast-paced world, access to timely and accurate healthcare information is critical, yet many individuals face challenges in assessing their symptoms, finding appropriate care, and understanding potential treatments. To address these issues, we propose HealthGuardian, an AI-powered clinical decision support system designed to assist users with symptom checking, personalized treatment recommendations, healthcare provider suggestions, online consultations, and early-stage diabetes prediction. HealthGuardian allows users to input their symptoms through natural language processing (NLP) and a recur-rent neural network (RNN) model, providing possible diagnoses and advising when to seek medical attention. The system offers personalized treatment plans based on medical history, suggests nearby healthcare providers using the Overpass API, and facilitates online consultations with doctors. Additionally, it features a predictive tool for early-stage diabetes risk assessment using various machine learning algorithms. The system leverages machine learning algorithms such as logistic regression, decision tree classifier, Naive Bayes, and random forest classifier to enhance diagnostic accuracy and prediction reliability. Our results demonstrate that HealthGuardian improves early diagnosis accuracy, provides actionable treatment guidance, and increases healthcare accessibility, helping users make informed decisions about their health.

关键词： Logistic regression Accuracy machine learning algorithms Neural networks Medical services Diabetes Reliability Risk management Medical diagnostic imaging Random forests

来源：评论

学校读者我要写书评

暂无评论

The Age and Gender Detection using Deep Convolution Neural Network

The Age and Gender Detection using Deep Convolution Neural N...

引用

Signal Processing and Advance Research in Computing (SPARC), International Conference on

作者： Shweta Chauhan Rahul Kumar Bibek Kumar Department of artificial intelligence and Machine Learning Madhav Institute of science and technology Gwalior Madhya Pradesh India ECE Department GLA University Mathura Uttar Pradesh India School of Data Science Symbiosis University of Applied Sciences Indore Madhya Pradesh India

ISBN: (数字)9798350385205

ISBN: (纸本)9798350385212

Automatic age and gender classification has become important researcher since the rise of social platforms and social media. The main advancements in face recognition are the ability to determine a person's age and gender. This paper makes a significant contribution by providing a survey of different face recognition methods for determining age and gender. A deep neural network (DNN) known as a convolutional neural network is frequently used for natural language processing and image recognition and processing. The proposed method significantly enhances three elements: face alignment, face recognition, and face recognition accuracy. All weight vectors of people in the same age group within a given database are averaged together. To predict gender and age, picture classification and regression models have been discussed in this paper respectively. Although training the proposed network to make accurate predictions takes a lot of time, it significantly improves age and gender categorization precision. From the experimental results we compared and analyzed the work to the most recent UTK-Face benchmark for estimating age and gender.

关键词： Training Surveys Accuracy Image recognition Social networking (online) Face recognition Predictive models Vectors Natural language processing Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

THE RANDOM FEATURE METHOD FOR TIME-DEPENDENT PROBLEMS

arXiv

引用

arXiv 2023年

作者： Chen, Jingrun Weinan, E. Luo, Yixin School of Mathematical Sciences University of Science and Technology of China Hefei230026 China Suzhou Institute for Advanced Research University of Science and Technology of China Suzhou215123 China AI for Science Institute Beijing and Center for Machine Learning Research School of Mathematical Sciences Peking University China University of Science and Technology of China Hefei230026 China

We present a framework for solving time-dependent partial differential equations (PDEs) in the spirit of the random feature method. The numerical solution is constructed using a space-time partition of unity and random feature functions. Two different ways of constructing the random feature functions are investigated: feature functions that treat the spatial and temporal variables (STC) on the same footing, or functions that are the product of two random feature functions depending on spatial and temporal variables separately (SoV). Boundary and initial conditions are enforced by penalty terms. We also study two ways of solving the resulting least-squares problem: the problem is solved as a whole or solved using the block time-marching strategy. The former is termed "the space-time random feature method" (ST-RFM). Numerical results for a series of problems show that the proposed method, i.e. ST-RFM with STC and ST-RFM with SoV, have spectral accuracy in both space and time. In addition, ST-RFM only requires collocation points, not a mesh. This is important for solving problems with complex geometry. We demonstrate this by using ST-RFM to solve a two-dimensional wave equation over a complex domain. The two strategies differ significantly in terms of the behavior in time. In the case when block time-marching is used, we prove a lower error bound that shows an exponentially growing factor with respect to the number of blocks in time. For ST-RFM, we prove an upper bound with a sublinearly growing factor with respect to the number of subdomains in time. These estimates are also confirmed by numerical *** Codes 65M20, 65M55, 65M70 Copyright © 2023, The Authors. All rights reserved.

关键词： Numerical methods

来源：评论

学校读者我要写书评

暂无评论

Enhancing Interpretability: The Role of Explainable AI in Healthcare Diagnostics

Enhancing Interpretability: The Role of Explainable AI in He...

引用

Electronics and Renewable Systems (ICEARS), International Conference on

作者： Nikita Zade Meher Langote Prateek Verma Department of Artificial Intelligence & Data Science Faculty of Engineering & Technology Datta Meghe Institute of Higher Education (DU) Sawangi Maharashtra India Department of Artificial Intelligence & Machine Learning Faculty of Engineering & Technology Datta Meghe Institute of Higher Education (DU) Sawangi Maharashtra India

ISBN: (数字)9798331509675

ISBN: (纸本)9798331509682

XAI is now transforming the use of AI in diagnosing diseases by overcoming some of the problems inherent in most black-box approaches. In time-sensitive speciality areas like computer-aided diagnosis, image analysis, and predictive modelling, SHAP, LIME, and attention-based XAI techniques explain how AI decides to help doctors and other healthcare professionals trust AI. Therefore, this paper aims to clarify why XAI is needed in healthcare, introduce techniques, and show their examples in cancer diagnosis and disease prognosis. XAI improves diagnostic performance and satisfies regulatory and ethical requirements for increased usage in clinical practice. Because of XAI, clinicians can use the best of artificial intelligence to complement their knowledge in enhancing the treatment of patients. That is why the outlook of XAI in healthcare includes the next steps in achieving higher scalability, managing bias, and working with diverse regulatory frameworks, which will define the future of AI solutions in healthcare.

关键词： Renewable energy sources Explainable AI Scalability Closed box Medical services Predictive models Regulation Artificial intelligence Prognostics and health management Cancer

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Review of Mojo: A High-Performance Programming Language

A Comprehensive Review of Mojo: A High-Performance Programmi...

引用

Mobile Computing and Sustainable Informatics (ICMCSI), International Conference on

作者： Parth Dhananjay Akre Utkarsha Pacharaney Department of Artificial Intelligence and Data Science Faculty of Engineering and Technology Datta Meghe Institute of Higher Education and Research Wardha Maharashtra India Department of Artificial Intelligence and Machine Learning Faculty of Engineering and Technology Datta Meghe Institute of Higher Education and Research Wardha Maharashtra India

ISBN: (数字)9798331522667

ISBN: (纸本)9798331522674

As artificial intelligence continues to advance at an unprecedented pace, the selection of programming languages significantly affects development processes, workflows, and outcomes. Mojo, a novel programming language, has gained attention through its integration of Python-like syntax, Rust-inspired safety features, and superior performance characteristics. This paper evaluates Mojo across four critical dimensions: distinctive features, performance metrics, ecosystem maturity, and practical applications, while examining potential adoption barriers. Positioned at the intersection of high-level programming simplicity and low-level performance optimization, Mojo demonstrates particular utility for artificial intelligence developers requiring both flexibility and computational efficiency. Through analysis of prominent libraries, including Endia, Lightbug HTTP, Basalt, and ***, this study examines Mojo's capabilities and limitations. By presenting a comparative analysis of Mojo's features, emerging ecosystem, and applicability to artificial intelligence development, this research addresses the current literature gap and provides substantive insights into this emerging programming language.

关键词： Reviews Ecosystems Syntactics Programming Libraries Real-time systems Safety Artificial intelligence Optimization Python

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：