Dies ist eine Übersichtsseite mit Metadaten zu dieser wissenschaftlichen Arbeit. Der vollständige Artikel ist beim Verlag verfügbar.
AI Access Hub: Automating Machine Learning for Non-Tech Users
0
Zitationen
4
Autoren
2025
Jahr
Abstract
The paper introduces an AI-powered web application designed to simplify machine learning for users with limited technical expertise. The platform automates the entire process, from data collection to model training and optimization. Using JSON-file techniques, users can effortlessly scrape web data and compile substantial image datasets. These datasets are preprocessed and fed into AutoKeras, an Automated Machine Learning (AutoML) library, which selects and fine-tunes the most accurate model. The optimized model is then made available for download directly from the platform, eliminating the need for expertise in dataset preparation, preprocessing, model training, or optimization.The web application features a user-friendly interface, with a frontend built using HTML and CSS and a backend powered by Python’s Flask framework. By integrating automated web scraping, dataset creation, AutoML-driven optimization, and a streamlined interface, the platform enables non-technical users to create and deploy advanced AI models effortlessly. This innovative approach empowers users to explore AI applications, bringing powerful machine learning tools within reach for anyone, regardless of their technical background.
Ähnliche Arbeiten
Rethinking the Inception Architecture for Computer Vision
2016 · 30.755 Zit.
MobileNetV2: Inverted Residuals and Linear Bottlenecks
2018 · 25.096 Zit.
CBAM: Convolutional Block Attention Module
2018 · 21.952 Zit.
An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
2020 · 21.527 Zit.
Xception: Deep Learning with Depthwise Separable Convolutions
2017 · 18.769 Zit.