Integrative AI often relies on combined models of multiple AI techniques and there are many ways to create those models and the algorithms that act on them.
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
The project AIRoutePlan (i.e.: Artificial Intelligence for Route Planning) aims to develop a toolkit for solving a wide range of route planning problems of the logistics sector.
A repository with some of the models developed and trained for the AI4Hotels project.
A new loss function for self-supervised representation learning, which is based on the whitening of the latent space features.
A flexible and extensible synthetic data generation engine based on mainstream statistics distributions and on timeseries generative AI techniques.
A tool to allow Visual Transformers (VTs) to learn spatial relations within an image making the VT training much more robust when training data is scarce. The tool can be used jointly with the standard (supervised) training and it does not depend on speci...
In the energy landscape that DSOs find themselves in today, predicting demand and the generation capacity of the systems to which they distribute becomes essential. This is mainly due to the injection of renewable energy among the consumers of the network...
A holistic learning framework for Novel Class Discovery (NCD), which adopts contrastive learning to learn discriminate features with both the labeled and unlabeled data. The Neighborhood Contrastive Learning (NCL) framework effectively leverages the local...
In Deep Micro-Dictionary Learning and Coding Networks fundamental convolutional layers are replaced by novel compound dictionary learning and coding layers.