Deep Learning

AI Assets related to #Deep Learning

ML Model

4k Video Super-Resolution Detection

This model detects upscaled 4k videos and identifies the upscaling model used.

Library

Deep Quality Diversity

Open-Ended Evolution for Minecraft Building Generation

Dataset

The Aristotle University of Thessaloniki (hereinafter, AUTH) created the following dataset, entitled ‘Flood Master Database’, within the context of the project TEMA that was funded by the European Commission-European Union [Grant Agreement number: 1010930...

Dataset

Blaze Fire Classification – Segmentation Dataset

The Aristotle University of Thessaloniki (hereinafter, AUTH) created the following dataset, entitled ‘Blaze’, within the context of the project TEMA that was funded by the European Commission-European Union [Grant Agreement number: 101093003; start date: ...

As a Service

DeepTSF

A machine learning operations (MLOps) framework for time series forecasting

Docker container

Blueberry Row Detection

Deep learning algorithm for segmenting blueberry rows within orchards using UAV multispectral images. This work has been carried out in the scope of the H2020 FlexiGroBots project, which has been funded by the European Commission in the scope of its H...

Dataset

Mastodon posts dataset

The Aristotle University of Thessaloniki created the Mastodon posts dataset within the context of the project TEMA (Trusted Extremely Precise Mapping and Prediction for Emergency Management; Grant Agreement No. 101093003; Call: HORIZON-CL4-2022-DATA-01; T...

Dataset

MOBISERV-AIIA Database

Eating and Drinking Activity Recognition Database (MOBISERV-AIIA Database) was created in order to fulfill the need for a good benchmarking database for the evaluation of specialized meal intake (such as eating and drinking) activity recognition algorithm...

Dataset

AUTH UAV Gesture Dataset

The AUTH UAV Gesture Dataset (created by AUTH in the context of the “AERIAL-CORE” collaborative project, funded from the European Union’s Horizon 2020 research and innovation programme) contains videos depicting human subjects performing 6 classes of gest...

As a Service

THRUST-AID: AI Diagnostics for aerial electricity grid inspections

THRUST-AID is an AI-powered automatic powerline defect detection tool, trained on extensive ultra-high resolution aerial imagery data selected from the entire Lithuania’s transmission network. The developed AI analytics software is able to identify high-r...

ML Model

THRUST-AID: Clearing Object Detection Model

THRUST-AID YOLOv8-based Clearing Object Detection model will help investigate the surroundings of the powerline based on RGB aerial data and indicate potential threats

As a Service

THRUST-4RESST

THRUST-4RESST is a multifunctional forest condition assessment tool that is based on AI-aided analytics of time-resolved satellite data

Education resources related to #Deep Learning

Short e-course on Cloud/Edge Computing for Deep Learning and Big Data Analytics

This short course on Cloud/Edge Computing for Deep Learning and Big Data Analytics provides a comprehensive overview and detailed presentation of advanced technologies utilized in distributed computational systems. Distributed computing plays a critical r...

Short course on Deep Learning and Computer Vision for Industrial Infrastructure Inspection

This short course on Deep Learning and Computer Vision for Industrial Infrastructure Inspection offers a comprehensive overview and in-depth presentation of various computer vision and deep learning challenges encountered during the inspection of industri...

From Cloud to Edge through Microservices

This short course on Big Data Analytics for Natural Disaster Management (NDM) provides a comprehensive overview and in-depth presentation of advanced technologies involved in the acquisition and analysis of Big Data for NDM. NDM can be greatly improved by...

Data Storytelling and Big Data value chain in Natural Disaster Management

Deep Learning for Post-Earthquake Safety Evaluation of Masonry Buildings

Short course on Big Data Analytics for Natural Disaster Management

Transfer Learning Lecture

Nowadays, Artificial Intelligence, notably Advanced Machine Learning (ML) drives scientific and economic growth worldwide. They are essentially massive ‘learning by experience/examples’ systems. However, as our tasks and the world change, such systems sho...

Deep Reinforcement Learning Lecture

From Statistical Methods to Deep Learning, Automatic Keyphrase Prediction: A Survey

Keyphrase prediction is a significant task in natural language processing that aims to generate concise phrases summarizing a document. Researchers have conducted extensive studies using statistical and deep learning methods, as well as incorporating exte...

Geometric deep learning

Geometric deep learning is an emerging field at the intersection of deep learning and graph theory, aimed at analyzing and processing structured data such as graphs, meshes, point clouds, and manifolds. Traditional deep learning models have primarily focu...

Advanced Deep Learning Module

Neural Networks and Deep Learning Module

Nowadays, Artificial Intelligence drives scientific and economic growth worldwide. This is largely due to advances in Machine Learning (ML), notably in Deep Neural Networks (DNNs), which are essentially massive ‘learning by experience/examples’ systems. T...

Documents related to #Deep Learning

Contribution of artificial deep learning for image segmentation in medical imaging

Read more about Contribution of artificial deep learning for image segmentation in medical imaging

An important task in image analysis is image segmentation. Once this key task done, there are huge of applications which can be done. Of course, the more accurate the segmentation, the better the quality of the applications. Deep learning algorithms can improve image segmentation. Their improvement offers new perspectives for the development and implementation of imaging biomarkers in clinical routine.

Interests of new deep learning image reconstruction algorithms for the improvement of image quality and the potential for dose reduction in CT

Read more about Interests of new deep learning image reconstruction algorithms for the improvement of image quality and the potential for dose reduction in CT

Deep learning has recently showed a great potential in imaging, notably to improve image quality. CT manufacturers have used this new AI technique to develop new reconstruction algorithms based on deep learning. The first results obtained with these new algorithms confirm the improvement of image quality compared to that with iterative reconstruction algorithms. The first results are very promising with the implementation of low-dose protocols and a great interest for ultra- low dose protocols.