Skip to content
Free planNo credit card requiredStart writing
AI for Research home
AI for Research home
Dashboard
Sign inGet started

Search 250 million research papers

Read the abstract, see who wrote it and who cites it, and get the citation in APA, MLA, Chicago or Harvard.

About 10,000 papers for “Machine Learning and Algorithms”

Algorithms and Machine Learning

Mitra, Manu · Zenodo (CERN European Organization for Nuclear Research) · 2019

Machine learning is a model that learns patterns in data and then calculates similar patterns in new data. For instance, if you want to categorize children’s books, it would mean that instead of setting up exact instructions for what establishes a children’s books, experts can set the computer hundreds of examples of children’s books. Then the computer find the pattern in that books and uses that pattern to recognize future books in that particular category. However, Machine Learning is actually a subset of artificial intelligence that assists computers to learn without explicitly programmed with predefined instructions. It concentrates on development of computer applications that can teach themselves to develop and change when open to new data. This calculation ability, in addition to the computer’s ability to process massive amounts of data; it supports machine learning to handle complex business conditions with efficiency and preciseness.

Cited by 0Open access

Machine learning architectures and algorithms

Marijo Zirdum · Repository of the University of Slavonski Brod · 2025

S obzirom na sve brži razvoj softverskih rješenja i rastući broj korisnika koji stvaraju velike količine podataka, razvijen je velik broj algoritama i metoda za primjenu strojnog učenja. Svrha razvoja navedenih tehnologija jest omogućiti izgradnju rješenja koja se oslanjaju na analizu podataka bez potrebe za ručnim programiranjem svakog pojedinog koraka u procesu donošenja odluka. Strojno učenje koristi različite algoritme i arhitekture kako bi omogućilo računalima da uče iz podataka i donose odluke bez eksplicitnog programiranja. Algoritmi poput regresije, stabala odlučivanja, SVM-a i neuronskih mreža omogućuju rješavanje raznih zadataka, ovisno o vrsti podataka i ciljevima analize. S razvojem dubokog učenja, sve veću važnost imaju složene arhitekture poput konvolucijskih i rekurentnih neuronskih mreža te Transformer modela, koji omogućuju učinkovitu obradu slike, govora i teksta. Odabir odgovarajuće kombinacije algoritma i arhitekture ključan je za uspješnu primjenu strojnog učenja u praksi. U današnje vrijeme se tehnike strojnog učenja široko primjenjuju u raznim područjima poput računarstva, medicine, poljoprivrede, ekonomije i brojnih drugih znanosti. Njihova sposobnost prilagodbe različitim vrstama problema, skalabilnost te brz odgovor na nove i nepoznate situacije čine ih iznimno popularnim i učinkovitim rješenjem u suvremenim istraživanjima i primjenama.

Cited by 0

Machine learning predictions and algorithms

zexia, zhang · Zenodo (CERN European Organization for Nuclear Research) · 2024

This repository presents a package that includes convolution neural network algorithms and prediction results for bed shear stress and bed topography.

Cited by 0Open access

Machine Learning: Algorithms and Applications

Mohssen Mohammed, Muhammad Badruddin Khan, Eihab B. M. Bashier · 2016

Machine learning, one of the top emerging sciences, has an extremely broad range of applications. However, many books on the subject provide only a theoretical approach, making it difficult for a newcomer to grasp the subject material. This book provides a more practical approach by explaining the concepts of machine learning algorithms and describing the areas of application for each algorithm, using simple practical examples to demonstrate each algorithm and showing how different issues related to these algorithms are applied.

Cited by 233

Machine Learning Algorithms and Measurement

Q. Chelsea Song, Ivan Hernandez, Hyun Joo Shin et al. · Cambridge University Press eBooks · 2023

This chapter provides an overview of the common machine learning algorithms used in psychological measurement (to measure human attributes). They include algorithms used to measure personality from interview videos; job satisfaction from open-ended text responses; and group-level emotions from social media posts and internet search trends. These algorithms enable effective and scalable measures of human psychology and behavior, driving technological advancements in measurement. The chapter consists of three parts. We first discuss machine learning and its unique contribution to measurement. We then provide an overview of the common machine learning algorithms used in measurement and their example applications. Finally, we provide recommendations and resources for using machine learning algorithms in measurement.

Cited by 1

WGCNA and machine learning algorithms.

Shushu Wang (6870191), Kachun Lu (20454740), Liwen Lin (2056903) et al. · Figshare · 2024

<p>A: Scale-free topology fit index and average connectivity analysis for the GSE100927 dataset. B: Dendrogram of the GSE100927 dataset, where the upper part shows the hierarchical clustering of genes, and the lower part shows gene modules, also known as network modules. C: Heatmap of gene correlations with the AS phenotype in the GSE100927 dataset. The color blocks on the left represent modules, and the color bars on the right indicate the range of correlation; the darker the color in the heatmap, the higher the correlation, with red indicating positive correlation and blue indicating negative correlation. Each cell contains numbers representing correlation strength and significance. D: Scale-free topology fit index and average connectivity analysis for the GSE89632 dataset. E: Dendrogram of the GSE89632 dataset, displaying clustering of genes into modules. F: Heatmap of gene correlations with the NAFLD phenotype in the GSE89632 dataset. G: Venn diagram of the intersection of key module genes from AS and NAFLD with CGs, yielding 48 Key Genes. H-I: Lasso regression analysis on the 48 Key Genes to compute diagnostic biomarkers’ lambda (λ) value (H) and its minimum value (I).</p>

Cited by 0Open access

Machine Learning and Deep Learning: Algorithms and Applications

V. Rekha, Uma Shankari S. · 2023

Machine learning is a subfield of artificial intelligence (AI) that involves the development of algorithms that can learn patterns from data and make predictions or decisions without being explicitly programmed. Deep learning is a subset of machine learning that uses deep neural networks with multiple layers to learn and extract features from complex data. The history of machine learning can be traced back to the 1950s, with the development of perceptrons, a type of artificial neuron. However, progress was slow until the 1990s, when the availability of large datasets and more powerful computing resources enabled the development of more sophisticated algorithms. In recent years, deep learning has achieved remarkable success in a wide range of applications, such as image recognition, speech recognition, and natural language processing. Machine learning and deep learning are important because they enable computers to perform tasks that were previously thought to be the exclusive domain of humans. They have the potential to revolutionize many industries, such as healthcare, finance, and transportation, by automating tasks and improving decision-making. However, they also raise ethical and societal concerns, such as bias and job displacement, that need to be addressed.

Cited by 0