Science topic
Machine Learning - Science topic
Explore the latest publications in Machine Learning, and find Machine Learning experts.
Publications related to Machine Learning (10,000)
Sorted by most recent
Deep materials informatics is a rapidly evolving field that employs deep learning techniques to develop predictive models for materials science. It involves the use of large datasets, advanced algorithms, and highperformance computing to extract key features from complex materials data. The aim of deep materials informatics is to speed up the proce...
Due to the enormous volume of data produced by the IoT, effective intrusion detection is necessary to protect confidential and sensitive information before an attack. This article presents a five-layered system for detecting intrusion in huge datasets. This work uses the construction of brand-new specialized features to increase the rate at which t...
Book review of Algorithmic Mathematics in
Machine Learning by Bastian Bohn, Jochen
Garcke and Michael Griebel
By leveraging the power of machine learning (ML) techniques, particularly Transformer technology, this study examines the validity of a conceptual model involving downscaling and upscaling to determine important factors for predictability (Shen et. al. 2010a, b). Providing a proof of concept, chaotic data from our recently-developed generalized Lor...
Student behavior is a multifaceted phenomenon influenced by numerous factors, including personal characteristics, environmental conditions, and academic experiences. Traditional methods for assessing student behavior often rely on subjective evaluations, such as teacher assessments, which can be inconsistent. In recent years, there has been an incr...
This paper proposes a novel domain decomposition (DD) method for the parametric reduced-order model based on the Physics-Data Combined Neural Network (DD-PDCNN). The computational domain is partitioned into a number of subdomains, and a Physics-Data Combined Neural Network (PDCNN) is constructed for each subdomain, which not only represents the dyn...
Machine learning (ML) holds immense potential for enterprise data use cases, but a lack of skilled data scientists hinders its utilization. Automated ML (AutoML) aims to empower business users but often falls short, especially when domain knowledge influences model selection. It remains unclear how human-guided ML (HGML) systems can effectively emp...
This review focuses on recent advancements in data-driven methods for analyzing flow and transport in porous media, which are showing promising potential for applications in energy, chemical engineering, environmental science, and beyond. We highlight novel methodologies driven by machine learning (ML), including image-based techniques, data-driven...
Statistical learning theory is the foundation of machine learning, providing theoretical bounds for the risk of models learned from a (single) training set, assumed to issue from an unknown probability distribution. In actual deployment, however, the data distribution may (and often does) vary, causing domain adaptation/generalization issues. In th...
Recently, interpretable machine learning has re-explored concept bottleneck models (CBM). An advantage of this model class is the user's ability to intervene on predicted concept values, affecting the downstream output. In this work, we introduce a method to perform such concept-based interventions on pretrained neural networks, which are not inter...
The Catalyst Project involves leveraging AWS services for a comprehensive data-driven approach in catalyst research. It encompasses data collection from various sources, storage and management using AWS tools, advanced analytics, machine learning, and AI applications for catalyst prediction and optimization. The project also focuses on containeriza...
AI technologies have rapidly advanced, bringing transformative changes to various industries and aspects of daily life. However, the rise of AI has also raised significant ethical concerns regarding fairness, transparency, accountability, and privacy. This chapter delves into the development of responsible and transparent machine learning models, e...
The recent breakthroughs in large-scale DNN attract significant attention from both academia and industry toward distributed DNN training techniques. Due to the time-consuming and expensive execution process of large-scale distributed DNN training, it is crucial to model and predict the performance of distributed DNN training before its actual depl...
While high-entropy alloys (HEAs) present exponentially large compositional space for alloy design, they also create enormous computational challenges to trace the compositional space, especially for the inherently expensive density functional theory calculations (DFT). Recent works have integrated machine learning into DFT to overcome these challen...
Potholes pose significant threats to vehicular movement, causing damage to
vehicles and risking the safety of drivers and pedestrians. The escalating
issue of potholes has led to substantial financial losses for vehicle owners
and drivers. Traditional methods of pothole detection are impractical,
necessitating an innovative approach. The study...
The concepts of precision, and accuracy are domain and problem dependent. The simplified numeric hard and soft measures used in the fields of statistical learning, many types of machine learning, and binary or multiclass classification problems are known to be of limited use for understanding the meaningfulness of models or their relevance. Arguabl...
This Special Issue, entitled "Applications of Machine Learning and Optimization in Energy Sectors", aims to explore the innovative and transformative potential of machine learning (ML) and optimization techniques to address critical challenges within the energy industry. With the increasing global demand for sustainable and efficient energy solutio...
https://elearn.nptel.ac.in/shop/iit-workshops/ongoing/micro-and-nano-architected-mechanical-metamaterials-multi-scale-physics-based-simulations-coupled-with-machine-learning/?v=79cba1185463
The education management system is an important tool for universities to manage academic information and information of staff and students. The article constructs a user behavior analysis model based on machine learning and a user behavior prediction model based on LR-XGBoost to analyze and predict user behavior in the educational management inform...
Nowadays, more and more legal decisions are being made with the help of machine learning models and algorithmic drives. Avoiding or reducing human bias in the decision-making process is extremely important for the fairness and transparency of the algorithms in legal decision support systems, and also profoundly affects the fairness and transparency...
Various fields in real life have increasingly utilized machine learning methods and data mining technology in recent years. This paper creates a data-driven model to implement intelligent human resource management in colleges and universities. The model utilizes the fuzzy decision tree algorithm to assist colleges and universities in selecting the...
In the modern business environment, sustainability and technological innovation have become paramount to achieving long-term growth. As organizations increasingly face environmental and economic pressures, sustainable IT and machine learning (ML) offer promising solutions to improve efficiency and reduce environmental impact. This article explores...
In the background of increasing translation content, it is no longer possible to rely solely on human translation to solve the problem of cross-language communication, and thus machine translation technology has gradually become an important means to solve the language barrier. In this paper, the semantic content features are extracted from univers...
This paper proposes the preliminary architecture of the cultural tourism corpus in accordance with the requirements of cultural tourism translation accuracy and fluency and further optimizes the structure of the architecture by combining it with the cultural tourism translation quality evaluation standards. Using the simple Bayesian classifier and...
The concept of Industry 5.0 signifies a new age in manufacturing, marked by the comprehensive integration of artificial intelligence (AI) throughout all production levels. This chapter explores the transformative potential of AI in significantly improving manufacturing processes, optimizing performance, and driving innovation. The chapter explores...
Integrating Artificial Intelligence (AI) and Machine Learning (ML) into clinical and biomedical fields revolutionizes healthcare by enhancing diagnostic accuracy, personalizing treatment, and streamlining operational efficiencies. This review explores recent advancements driven by AI/ML technologies, highlights their implications for patient care,...
Although some studies employed technical indicators as input to machine learning models to forecast stock trading signals, there was a noticeable gap between how technical analysts and machine learning professionals used technical indicators. Based on this finding, this study suggested a know sure thing based machine learning (KST-ML) technique for...
Modelling water futures is challenging due to the dynamics of several variables and non-linearity. The traditional models are often inefficient to capture such hidden patterns. Thus, utilizing datasets that include daily price and volume information of water futures, this study evaluates the performance of SVM, Random Forest Regressor, LSTM, GBM, a...
In the fast changing world of artificial intelligence and machine learning, among the critical determinants of success in AI implementations are data quality and quantity. Acquisition, processing, storage, and real time applications are investigated in this comprehensive analysis of the fundamental challenges and considerations in data management....
AI in content creation is transforming how digital content is produced, optimized, and personalized. Leveraging machine learning and natural language processing, AI can streamline content creation by generating written content, improving grammar and tone, analyzing audience preferences, and even creating multimedia assets like images and videos
The Pre-Planck epoch, a period preceding the Planck time (10^-43 seconds), remains one of the most enigmatic phases in cosmology. Traditional models struggle to provide insights into this era, owing to the absence of empirical data and the limitations of existing theoretical frameworks. However, recent advances in artificial intelligence (AI), part...
This paper explores the role of Artificial Intelligence (AI) in assessing the usefulness of Figenbaum's Number, a constant that emerges from the study of chaotic systems and bifurcation theory in mathematics. By leveraging machine learning algorithms, particularly neural networks, the paper investigates how AI can assist in identifying practical ap...
Background
Depressed individuals have both heightened negative self-views and reduced positive self-views. The self-referential encoding task (SRET) can capture depressed individuals’ self-schemas by asking them to endorse whether a word describes them or not. Digital interventions that target positive biases in depression can help improve positive...
Detecting malware remains a significant challenge, as malware authors constantly develop new techniques to evade traditional signature-based and heuristic-based detection methods. This paper proposes a novel approach to malware detection that analyzes patterns in Windows system calls sequences to identify malicious behaviors. We use a voting classi...
Accurate and reasonable cement take prediction is of great significance for effective control of dam foundation grouting quality and cost. This article combined the previous research results and engineering practice to explore the different influencing factors of cement take, and conducted parameter correlation analysis to determine the input param...
Gravity data, comprising a key foundational dataset, are crucial for various research, including land subsidence monitoring, geological exploration, and navigational positioning. However, the collection of gravity data in specific regions is difficult because of environmental, technical, and economic constraints, resulting in a non-uniform distribu...
Training machine learning models for tasks such as de novo sequencing or spectral clustering requires large collections of confidently identified spectra. Here we describe a dataset of 2.8 million high-confidence peptide-spectrum matches derived from nine different species. The dataset is based on a previously described benchmark but has been re-pr...
En el campo del aprendizaje automático, el álgebra lineal se ha consolidado como una herramienta matemática fundamental para el desarrollo y la optimización de algoritmos, permitiendo modelar y manipular grandes cantidades de datos de manera eficaz. Para abordar este objetivo, se realizó una revisión exhaustiva de la literatura relevante, centrada...
This book offers a step-by-step approach to understanding and implementing LLMOps in your projects. It's designed to be accessible to developers, researchers, and AI enthusiasts, guiding you through the tools and techniques required to harness the power of Hugging Face's cutting-edge AI platform. Whether you're new to the field or looking to expand...
Feature selection is crucial for minimizing redundancy in information and addressing the limitations of traditional classification methods when dealing with large datasets and numerous features in many machine learning applications. To improve the classification, this article introduced two hybrid methods utilizing a genetic algorithm and a gray wo...
Sea surface temperature anomalies (SSTAs) over the North Atlantic (NA) have a significant impact on the weather and climate in both local and remote regions. This study first evaluated the seasonal prediction skill of NA SSTA using the North American multi-model ensemble and found that its performance is limited across various regions and seasons....
The outbreak of epidemiological diseases creates a major impact on humanity as well as on the world's economy. The consequence of such infectious diseases affects the survival of mankind. The government has to stand up to the negative influence of these epidemiological diseases and facilitate society with medical resources and economical support. I...
Over the last several decades, recommender systems have become an integral part of both our daily lives and the research frontier at machine learning. In this survey, we explore various approaches to developing simulators for recommendation systems, especially for modeling the user response function. We consider simple probabilistic models, approac...
This study presents a current and extensive bibliometric analysis of pavement deterioration detection, monitoring , and assessment using various sensors alongside machine learning and deep learning algorithms. The impact of electronic sensors, machine learning, and deep learning on road pavement evaluation and monitoring within the transportation s...
Understanding the interactions between solutes and solvents is vital in many areas of the chemical sciences. Solvation free energy (SFE) is an important thermodynamic property in characterising molecular solvation and so accurate prediction of this property is sought after. The One-Dimensional Reference Interaction Site Model (RISM) is a well-estab...
The emergence of 3D and 4D printing has transformed the field of polymer composites, facilitating the fabrication of complex structures. As these manufacturing techniques continue to progress, the integration of machine learning (ML) is widely utilized to enhance aspects of these processes. This includes optimizing material properties, refining pro...
After the introduction of large language models (LLMs), science has not remained the same. Researchers from several different fields of science have been rushing to conduct research on LLMs. This is due to the fact that LLMs are no longer something only machine learning experts can understand. As the middle L in LLM stands for language, it is evide...
Congenital heart disease (CHD) is a major cause of infant mortality and presents life-long challenges to individuals living with these conditions. Genetic causes are known for only a minority of types of CHD. Discovering further genetic causes is limited by challenges in prioritising candidate CHD genes. We examined a wide range of features of mous...
Federated Learning (FL), as a distributed machine learning framework, can effectively learn symmetric and asymmetric patterns from large-scale participants. However, FL is susceptible to malicious backdoor attacks through attackers injecting triggers into the backdoored model, resulting in backdoor samples being misclassified as target classes. Due...
Eight major supply chains contribute to more than 50% of the global greenhouse gas emissions (GHG). These supply chains range from raw materials to end-product manufacturing. Hence, it is critical to accurately estimate the carbon footprint of these supply chains, identify GHG hotspots, explain the factors that create the hotspots, and carry out wh...
The matrix element method is the LHC inference method of choice for limited statistics. We present a dedicated machine learning framework, based on efficient phase-space integration, a learned acceptance and transfer function. It is based on a choice of INN and diffusion networks, and a transformer to solve jet combinatorics. We showcase this setup...
The transformation of renewable bio‐oil into value‐added chemicals and bio‐oil through catalytic processes embodies an efficient approach within the realm of advancing sustainable energy. Spinel‐based catalysts have garnered significant attention owing to their ability to precisely tune metals within the framework, thereby facilitating adjustments...
We explore the role of artificial intelligence (AI) in examining the stability of neutron stars within the context of a universe governed by a nonzero cosmological constant, Λ. Employing machine learning algorithms and neural networks, this study simulates the effects of Λ on the equilibrium states of neutron stars, evaluating potential impacts on...
High-quality method names are very significant for us to understand programs and maintain software efficiently. Giving concise and consistent method names can help developers understand such programs well, especially for inexperienced participants. The importance of the naming strategy to software engineering (SE) has attracted researchers from all...
Credit Cards can be used in online transactions due to the convenience and ease of use. Credit card fraud is one of the leading causes of financial losses for credit card issuers and finance companies. Card fraud has cost credit card companies money. Currently, card fraud detection is the most common problem facing credit card companies. Credit car...
This paper takes the students of neurology specialty in a medical school as the research object and analyzes the current situation of its educational team construction. A machine learning algorithm based on weighted plain Bayes is used to construct an evaluation model, through which different weights are given to each index to explore the effective...
Accurate air pollutant prediction is essential for addressing environmental and public health concerns. Air quality models like WRF-CMAQ provide simulations, but often show significant errors compared to observed concentrations. To identify the sources of these model biases, we applied the XGBoost machine learning algorithm to assess the performanc...
A pesquisa teve como objetivo geral compreender as soluções digitais e as possibilidades de aplicação na relação comercial entre fabricantes de produtos para automação industrial e os membros de seus canais de distribuição. Para tanto, foi realizada uma pesquisa de natureza qualitativa e de caráter exploratório, operacionalizada por meio de entrevi...
Neural fields or implicit neural representations (INRs) have attracted significant attention in machine learning and signal processing due to their efficient continuous representation of images and 3D volumes. In this work, we build on INRs and introduce a coordinate-based local processing framework for solving imaging inverse problems, termed LoFi...
Query optimization has become a research area where classical algorithms are being challenged by machine learning algorithms. At the same time, recent trends in learned query optimizers have shown that it is prudent to take advantage of decades of database research and augment classical query optimizers by shrinking the plan search space through di...
With the increasing inference cost of machine learning models, there is a growing interest in models with fast and efficient inference. Recently, an approach for learning logic gate networks directly via a differentiable relaxation was proposed. Logic gate networks are faster than conventional neural network approaches because their inference only...
The Kullback–Leibler divergence (KL divergence) is a statistical measure that quantifies the difference between two probability distributions. Specifically, it assesses the amount of information that is lost when one distribution is used to approximate another. This concept is crucial in various fields, including information theory, statistics, and...
The Pacific decadal oscillation (PDO) is often described as a long-lived El Niño-like pattern of Pacific climate variability, and it has widespread climate and ecosystem impacts. PDO forecasts can provide useful information for policymakers on how to handle PDO impacts. Nevertheless, due to the long duration of the PDO cycles and their complex form...
A inteligência artificial (IA) desempenha um papel crucial no
Planejamento e Controle da Produção (PCP), auxiliando na tomada de decisões e na otimização de processos, aplicando técnicas avançadas como machine learning através de modelos orientados a dados e generativos para tarefas como programação da produção e previsão de demandas. Na Indústria...
Die Schwingungsspektroskopie ist eine weit verbreitete Technik zur chemischen Charakterisierung in verschiedenen analytischen Disziplinen. Ihre Anwendungen erstrecken sich zunehmend auf die Analyse komplexer Proben wie Bioflüssigkeiten und ermöglichen molekulares Profiling mit hohem Durchsatz. Trotz ihrer Leistungsfähigkeit leidet diese Technologie...
With recent environmental challenges, predicting climatic phenomena has become increasingly relevant to prevent major tragedies. One of the events that most affects large cities is rainfall, which, when occurring in above-normal volumes, can cause floods and inundations, impacting daily routines, public safety, and urban infrastructure. In this con...