Videos

This video presents a summary of the work carried out within Task 7.3, “Higher-level cognition for domestic assistance robots”, led by UC3M in the framework of the European ALMA project.

Explore the core functionality of the AML Dashboard—your entry point to building Algebraic Machine Learning models. This video introduces the Python-based tools available for defining, training, and evaluating world models in AML.

This video illustrates how ethical and cultural decisions made by the user influence driver behavior and accident outcomes within a simulation powered by the ALMA Human–AML co-learning platform.

AML-based world model updated following user-driven simulations involving ethical and cultural decisions.

Discover how to perform real-time image classification using the AML Dashboard! In this tutorial, we demonstrate how to capture live images from a webcam and classify each frame with a trained model.

Learn how to classify images in batches using the AML Dashboard.

In this tutorial, we guide you through the entire process effortlessly.

Learn how to easily fetch an AML model using the AML Dashboard! In this tutorial, we'll guide you step by step through the fetching process, from starting the backend server to receiving the model. Perfect for users, developers, and researchers exploring the AML framework.

Learn how to create and manage custom datasets for AML model training using the AML Dashboard. This step-by-step guide covers data preparation and integration to optimize your machine learning projects.

Learn how to train and optimize an AML model using the AML Dashboard. This quick tutorial covers model evaluation, fine-tuning, and real-time performance monitoring. Perfect for developers looking to enhance their ML projects.

How to interact with the Context Broker using the AML Dashboard. Learn how to create Fiware Nodes, send data, and retrieve inference results—all from the dashboard

Collaborative Learning Scenario using AML-IP nodes: Model Manager Receiver Node and Model Manager Sender Node. With these two nodes implemented in Python, users can deploy multiple instances to observe the behavior of a simulated AML-IP network in action.

This demo showcases implementing two types of nodes: the Inference Node and the Edge Node. By deploying multiple instances of each, users can observe the behavior of a simulated AML-IP network in action.

The following video demonstrates the process of:

• Connecting nodes over WAN.

• Performing distributed training.

Learn how to connect nodes over a Wide Area Network (WAN) using a client-server setup. This video walks you through:

• Creating a Client Node on the user’s side

• Setting up a Server Node on a remote network

An introduction to the principles of Algebraic Machine Learning for viewers without knowledge of basic abstract algebra.

Learn how to classify images in batches using the AML Dashboard. In this tutorial, we effortlessly guide you through the entire process.

Jaime Martín Losa, CEO of eProsima, and Raúl Sánchez-Mateos, Project Manager at eProsima, telecommunications Engineer from UPM, and Robotics Engineer from KTH, discussed eProsima's different roles in the ALMA project.

Victor Fortes Rey, a researcher at the German Research Center for Artificial Intelligence (DFKI) in Germany and a permanent researcher at INRIA Paris-Saclay, discussed DFKI´s role in the project.

Dr. Janin Koch, a permanent researcher at INRIA Paris-Saclay, discussed Inria's role in the project.

Dr. Fernando Martín Maroto, researcher at Champalimoud Foundation and co-fuounder at Algebraic AI, discussed Algebraic's role in the project.

Dr. Wendy Mackay a Research Director director at Inria and Professor at the Université Paris-Saclay, discussed Inria's role in the project.

Dr. Juan G Vitores, a Associate Professor at UC3M, discussed Inria's role in the project.