检索结果-内蒙古大学图书馆

Deterministic Uncertainty Estimation for Multi-Modal Regression With Deep Neural Networks

IEEE ACCESS 2025年 13卷 45281-45289页

作者： Cho, Jaehak Kim, Jae Myung Han, Seungyub Lee, Jungwoo Seoul Natl Univ Interdisciplinary Program Artificial Intelligence Cognit & Machine Learning Lab Seoul 08826 South Korea Seoul Natl Univ Dept Elect & Comp Engn NextQuantum Seoul 08826 South Korea Univ Tubingen Explainable Machine Learning Lab Cluster Excellence Machine Learning D-72076 Tubingen Germany

Prediction interval (PI) is a common method to represent predictive uncertainty in regression by deep neural networks. This paper proposes an extension of the prediction interval by using a union of disjoint intervals. Since previous PI methods assumed a single-interval PI (one lower and upper bound), it suffers from performance degradation in uncertainty estimation when the conditional density function is multi-modal. This paper demonstrates the need to include multi-modality in uncertainty estimation for regression. To address the issue, we propose a novel method that generates a union of disjoint PI's. With UCI benchmark experiments, the proposed method is shown to improve over current state-of-the-art uncertainty quantification methods, reducing an average PI width by over 27%. With qualitative experiments, it is shown that multi-modality often exists in real-world datasets, and our method produces high-quality PI's compared to existing PI methods.

关键词： Uncertainty Artificial neural networks Estimation Upper bound Ensemble learning Bayes methods Density functional theory Predictive models Optimization Mathematical models Deep learning uncertainty estimation multi-modal distribution regression

来源：评论

学校读者我要写书评

暂无评论

Overcoming Confounding Bias in Causal Discovery Using Minimum Redundancy and Maximum Relevancy Constraint

引用

IEEE ACCESS 2024年 12卷 33057-33068页

作者： Nadendla, Havisha Etha, Pujit Pavan Chowriappa, Pradeep Louisiana Tech Univ Data Min & Machine Learning Lab Program Comp Sci Coll Engn & Sci Ruston LA 71272 USA

Causal discovery is the process of modeling cause and effect relationships among features. Unlike traditional model-based approaches, that rely on fitting data to the models, methods of causal discovery determine the causal structure from data. In clinical and EHR data analysis, causal discovery is used to identify dependencies among features that are difficult to estimate using model-based approaches. The resultant structures are represented as Directed Acyclic Graphs (DAG) consisting of nodes and arcs. Here, the direction of the arcs in a DAG indicates the influence of one feature over the other. These dependencies are fundamental to the discovery of novel insights obtained from data. However, causal discovery solely relies on establishing feature dependencies based on their conditional dependencies, that could lead to inaccurate inferences brought about by confounding bias. Our contribution in this work is 'Non-Confounding Causal Discovery' (NCCD), a framework aimed at overcoming confounding bias leveraging maximum relevancy and minimum redundancy between features using the concepts of information theory. The work presented uses threshold conditioned values on which the features in the graphical structure are connected to one another. Validation was carried out on three clinical trial benchmark datasets and compared the results against the previously known Naive Bayes (NB) and Tree Augmented Naive Bayes (TAN) algorithms. We observe a reduction in the complexity of the graph, evidenced by a decrease in the number of arcs. Notably, the graphs generated through NCCD exhibited a capacity to eliminate confounding dependencies while concurrently preserving the overall score of the network.

关键词： Computational modeling Bayes methods Data models Redundancy Mutual information Probability distribution Filtering theory Graphical models Tree graphs Cause effect analysis Causal discovery confounding bias directed acyclic graphs information theory Naive Bayes tree augmented Naive Bayes

来源：评论

学校读者我要写书评

暂无评论

Mean-field analysis of synaptic alterations underlying deficient cortical gamma oscillations in schizophrenia

引用

JOURNAL OF COMPUTATIONAL NEUROSCIENCE 2025年第1期53卷 99-114页

作者： Song, Deying Chung, Daniel W. Ermentrout, G. Bard Carnegie Mellon Univ Neurosci Inst Joint Program Neural Computat & Machine Learning Pittsburgh PA 15213 USA Carnegie Mellon Univ Machine Learning Dept Pittsburgh PA 15213 USA Univ Pittsburgh Ctr Neural Basis Cognit Pittsburgh PA 15213 USA Univ Pittsburgh Dept Psychiat Translat Neurosci Program Pittsburgh PA 15213 USA Univ Pittsburgh Dept Math Pittsburgh PA 15213 USA

Deficient gamma oscillations in the prefrontal cortex (PFC) of individuals with schizophrenia (SZ) are proposed to arise from alterations in the excitatory drive to fast-spiking interneurons (E ->\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\rightarrow $$\end{document}I) and in the inhibitory drive from these interneurons to excitatory neurons (I ->\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\rightarrow $$\end{document}E). Consistent with this idea, prior postmortem studies showed lower levels of molecular and structural markers for the strength of E ->\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\rightarrow $$\end{document}I and I ->\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\rightarrow $$\end{document}E synapses and also greater variability in E ->\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\rightarrow $$\end{document}I synaptic strength in PFC of SZ. Moreover, simulating these alterations in a network of quadratic integrate-and-fire (QIF) neurons revealed a synergistic effect of their interactions on reducing gamma power. In this study, we aimed to inv

关键词： Mean-field model Gamma oscillations Cortical circuits Schizophrenia

来源：评论

学校读者我要写书评

暂无评论

Deep features based convolutional neural network to detect and automatic classification of white blood cells

引用

Journal of Ambient Intelligence and Humanized Computing 2023年第7期14卷 9191-9205页

作者： Yentrapragada, Divyateja Student of Postgraduate Program in Data Science and Machine Learning Graham School University of Chicago and Jigsaw Academy ChicagoIL60637 United States

White blood cells (WBCs) play an important role in the human body's immune system and it widely presented in the human body. Recently, the incidence of blood diseases related to WBC increases in the human body. In the research application, optimal WBC is a popular field for the diagnosis of blood disease, the optimal WBC count gives useful information. The Deep Features Based Convolutional Neural Network (DFCNN) is created in this research to detect the count of WBC and automated categorization using CNN from the picture database. With three phases, the proposed method working are feature extraction, feature selection, and classification phases. In the extraction phase, the Combined CNN structure is designed which is a combination of AlexNet, GoogLeNet, and ResNet-50 respectively. The combined CNN architecture is utilized to extract 3000 essential features from the image database. In the feature selection phase, the hybrid Mayfly Algorithm with Particle Swarm Optimization (HMA-PSO) is designed for selecting the essential feature from the feature sets. In the HMA-PSO algorithm, with the help of PSO algorithm, the velocity updating of the mayfly is achieved. The proposed classifier named Recurrent Neural Network-Long Short-Term Memory (RNN-LSTM), collects the selected features. This classifier is utilized to classify the WBC types such as Neutrophils, Eosinophils, Monocytes, and Lymphocytes respectively. The proposed method is implemented in the platform of MATLAB and performances are evaluated by statistical measurements such as precision, recall, specificity, accuracy, and F_Measure. The results of the proposed method are compared with the other existing methods such as MA-RNN and PSO-RNN respectively. © 2022, The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Feature importance analysis using ensemble decision tree models for aspirational luxury purchase intention of young cohorts in emerging markets

引用

JOURNAL OF DECISION SYSTEMS 2025年第1期34卷

作者： Nair, Manas Nair, Jessy Congruence Syst AI & Machine Learning Bengaluru India St Josephs Inst Management PGDM Program Bengaluru India Carnegie Mellon Univ Informat Networking Inst Pittsburgh PA 15251 USA

Millennial and Gen Z consumers in emerging countries form the biggest growth market for luxury businesses. While extant luxury research treats them as a homogenous unit, the Generational Cohort Theory proposes segmenting young consumers based on demographics. Using a conceptual framework developed through an extensive literature review, Random Forest regressors and Gradient Boosted Regression Trees are used to study the feature importances of the factors that drive Consumer Luxury Value and Luxury Purchase Intention. Ensemble tree methods are capable of capturing nonlinearities within the model and leverage the explainability of their decision tree learners to provide insight into the feature importances. Consumer Luxury Value, Other-directed and Experiential values are the most significant predictors of Luxury Purchase Intention across all gender and demographic cohorts with specific differences between cohorts. Gen Z consumers display stronger Other-Directed and Cost Perception values. Cohort-specific findings show Gen Z luxury consumers are more collectivistic than Millennials.

关键词： Feature importance luxury purchase intention Gen Z Millennials random forests gradient boosted trees

来源：评论

学校读者我要写书评

暂无评论

Ground-truthed and high-resolution drone images of the leafy spurge weed plant (Euphorbia esula)

引用

SCIENTIFIC DATA 2025年第1期12卷 1-7页

作者： Doherty, Kyle Gurinas, Max Samsoe, Erik Casper, Charles Larkin, Beau Ramsey, Philip Trabucco, Brandon Salakhutdinov, Ruslan MPG Ranch Aerial Survey Program Missoula MT 59833 USA Univ Chicago Lab Sch Chicago IL USA Carnegie Mellon Univ Dept Machine Learning Pittsburgh PA USA

This dataset comprises 1.3 cm resolution aerial images of grasslands in western Montana, USA, captured by a commercial drone. Many scenes contain leafy spurge (Euphorbia esula), introduced to North America, now widespread in rangeland ecosystems, which is highly invasive and damaging to crop production and biodiversity. Technicians surveyed 1000 points in the study area, noting spurge presence or absence, and recorded each point's position with precision global navigation satellite systems. We cropped tiles from an orthomosaic image at these locations. We publicly release these images and metadata as a Hugging Face Dataset, accessible in one line of code. Our aim is to invite the research community to develop classifiers as early warning systems for spurge invasion. We tested classification performance for two contemporary vision models and achieved 0.85 test accuracy. This demonstrates the feasibility yet difficulty of this classification task.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Combining a Chemical Language Model and the Structure-Activity Relationship Matrix Formalism for Generative Design of Potent Compounds with Core Structure and Substituent Modifications

引用

JOURNAL OF CHEMICAL INFORMATION AND MODELING 2024年第23期64卷 8784-8795页

作者： Chen, Hengwei Bajorath, Jurgen Univ Bonn Dept Life Sci Informat & Data Sci LIMES Program Unit Chem Biol & Med Chem B IT D-53115 Bonn Germany Univ Bonn Lamarr Inst Machine Learning & Artificial Intellig D-53115 Bonn Germany

In medicinal chemistry, compound optimization relies on the generation of analogue series (AS) for exploring structure-activity relationships (SARs). Potency progression is a critical criterion for advancing AS. During optimization, a key question is which analogues to synthesize next. We introduce a new computational methodology for the extension of AS with potent compounds containing both core structure and substituent modifications at multiple sites, which has been reported for the first time. The approach combines a transformer chemical language model (CLM) with a SAR matrix (SARM) methodology that identifies and organizes structurally related AS. Therefore, the SARM approach was expanded to cover multisite AS. Consensus series extracted from SARMs representing a potency gradient served as input for CLM training to extend test AS with potent analogues. Different model variants were derived and investigated. Both general and fine-tuned models correctly predicted known potent analogues at high positions in probability-based compound rankings and chemically diversified AS through core structure modifications of the generated candidate compounds and substituent replacements at multiple sites.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Rationalizing Predictions of Isoform-Selective Phosphoinositide 3-Kinase Inhibitors Using MolAnchor Analysis

引用

JOURNAL OF CHEMICAL INFORMATION AND MODELING 2025年第3期65卷 1357-1366页

作者： Lamens, Alec Bajorath, Juergen Rhein Friedrich Wilhelms Univ Dept Life Sci Informat & Data Sci LIMES Program Unit Chem Biol & Med Chem B IT D-53115 Bonn Germany Rhein Friedrich Wilhelms Univ Bonn Lamarr Inst Machine Learning & Artificial Intellig D-53115 Bonn Germany

Explaining the predictions of machine learning models is of critical importance for integrating predictive modeling in drug discovery projects. We have generated a test system for predicting isoform selectivity of phosphoinositide 3-kinase (PI3K) inhibitors and systematically analyzed correct predictions of selective inhibitors using a new methodology termed MolAnchor, which is based on the "anchors" concept from explainable artificial intelligence. The approach is designed to generate chemically intuitive explanations of compound predictions. For nearly all correctly predicted isoform-selective inhibitors, well-defined structural fragments determining the predictions were identified, and in most cases, an individual substructure was responsible for the prediction outcome. For inhibitors with different isoform selectivities, recurrent substructures determining the predictions were distinct. The comparison of newly identified anchor substructures with independent explanations based on calculated feature importance values supported the superior interpretability of MolAnchor explanations. Two highly recurrent substructures determining correct predictions were found to be directly implicated in isoform selectivity of PI3K inhibitors, thus indicating a causal relationship between decisive substructures and selectivity determinants.

关键词： Drug discovery

来源：评论

学校读者我要写书评

暂无评论

Generative design of compounds with desired potency from target protein sequences using a multimodal biochemical language model

引用

JOURNAL OF CHEMINFORMATICS 2024年第1期16卷 55页

作者： Chen, Hengwei Bajorath, Juergen Rhein Friedrich Wilhelms Univ Lamarr Inst Machine Learning & Artificial Intellig Dept Life Sci Informat & Data Sci LIMES Program Chem Biol & Med ChemB IT Friedrich Hirzebruch Allee 5-6 D-53115 Bonn Germany

Deep learning models adapted from natural language processing offer new opportunities for the prediction of active compounds via machine translation of sequential molecular data representations. For example, chemical language models are often derived for compound string transformation. Moreover, given the principal versatility of language models for translating different types of textual representations, off-the-beaten-path design tasks might be explored. In this work, we have investigated generative design of active compounds with desired potency from target sequence embeddings, representing a rather provoking prediction task. Therefore, a dual-component conditional language model was designed for learning from multimodal data. It comprised a protein language model component for generating target sequence embeddings and a conditional transformer for predicting new active compounds with desired potency. To this end, the designated "biochemical" language model was trained to learn mappings of combined protein sequence and compound potency value embeddings to corresponding compounds, fine-tuned on individual activity classes not encountered during model derivation, and evaluated on compound test sets that were structurally distinct from training sets. The biochemical language model correctly reproduced known compounds with different potency for all activity classes, providing proof-of-concept for the approach. Furthermore, the conditional model consistently reproduced larger numbers of known compounds as well as more potent compounds than an unconditional model, revealing a substantial effect of potency conditioning. The biochemical language model also generated structurally diverse candidate compounds departing from both fine-tuning and test compounds. Overall, generative compound design based on potency value-conditioned target sequence embeddings yielded promising results, rendering the approach attractive for further exploration and practical applications.

关键词： Deep learning Molecular design Protein language model Conditional transformer Active compounds

来源：评论

学校读者我要写书评

暂无评论

Human-in-the-Loop Evolution of Database Views for Data Exploration

Human-in-the-Loop Evolution of Database Views for Data Explo...

引用

2023 IEEE Latin American Conference on Computational Intelligence, LA-CCI 2023

作者： de Carvalho, Thiego Buenos Aires Martins, Denis Mayr Lima de Lima Neto, Fernando Buarque Computing Engineering Program University of Pernambuco Recife Brazil Machine Learning and Data Engineering University of Münster ERCIS Münster Germany

ISBN: (纸本)9798350348071

Under the increasingly complex and interconnected world we live in, data has become extremely valuable. Nevertheless, exploring even a simple database is not a trivial task, as it requires technical knowledge which many new and non-technical data users do not have. This task includes writing database queries to retrieve data, uncover insights, and exploit patterns. Furthermore, in large volumes of data, finding valuable data that matches a certain user’s purpose requirement is challenging, especially under restrictive time constraints. Typically, this task is manual, ad-hoc, and time-consuming. To address these challenges, researches have proposed tools to support data exploration tasks, especially by means of View Recommendation. However, current recommendation approaches require enumerating all candidate views that can be defined over an input database. In this work, we introduce a novel view recommendation method that leverages a human-in-the-loop approach to create, evaluate, and tailor views to match user intent. Our experimental evaluation on real-world data demonstrates that our approach suitably recommends views that capture multiple perspectives on the data at hand. © 2023 IEEE.

关键词： Data visualization

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：