Search Results for author: Natalia Díaz-Rodríguez

Found 26 papers, 11 papers with code

Connecting the Dots in Trustworthy Artificial Intelligence: From AI Principles, Ethics, and Key Requirements to Responsible AI Systems and Regulation

no code implementations2 May 2023 Natalia Díaz-Rodríguez, Javier Del Ser, Mark Coeckelbergh, Marcos López de Prado, Enrique Herrera-Viedma, Francisco Herrera

Trustworthy Artificial Intelligence (AI) is based on seven technical requirements sustained over three main pillars that should be met throughout the system's entire life cycle: it should be (1) lawful, (2) ethical, and (3) robust, both from a technical and a social perspective.

Ethics Fairness

Towards a more efficient computation of individual attribute and policy contribution for post-hoc explanation of cooperative multi-agent systems using Myerson values

1 code implementation6 Dec 2022 Giorgio Angelotti, Natalia Díaz-Rodríguez

A quantitative assessment of the global importance of an agent in a team is as valuable as gold for strategists, decision-makers, and sports coaches.

Exploring the Trade-off between Plausibility, Change Intensity and Adversarial Power in Counterfactual Explanations using Multi-objective Optimization

1 code implementation20 May 2022 Javier Del Ser, Alejandro Barredo-Arrieta, Natalia Díaz-Rodríguez, Francisco Herrera, Andreas Holzinger

To this end, we present a novel framework for the generation of counterfactual examples which formulates its goal as a multi-objective optimization problem balancing three different objectives: 1) plausibility, i. e., the likeliness of the counterfactual of being possible as per the distribution of the input data; 2) intensity of the changes to the original input; and 3) adversarial power, namely, the variability of the model's output induced by the counterfactual.

OG-SGG: Ontology-Guided Scene Graph Generation. A Case Study in Transfer Learning for Telepresence Robotics

1 code implementation21 Feb 2022 Fernando Amodeo, Fernando Caballero, Natalia Díaz-Rodríguez, Luis Merino

Scene graph generation from images is a task of great interest to applications such as robotics, because graphs are the main way to represent knowledge about the world and regulate human-robot interactions in tasks such as Visual Question Answering (VQA).

BIG-bench Machine Learning Graph Generation +4

Collective eXplainable AI: Explaining Cooperative Strategies and Agent Contribution in Multiagent Reinforcement Learning with Shapley Values

1 code implementation4 Oct 2021 Alexandre Heuillet, Fabien Couthouis, Natalia Díaz-Rodríguez

This study proposes a novel approach to explain cooperative strategies in multiagent RL using Shapley values, a game theory concept used in XAI that successfully explains the rationale behind decisions taken by Machine Learning algorithms.

Decision Making Explainable artificial intelligence +3

Efficient State Representation Learning for Dynamic Robotic Scenarios

no code implementations17 Sep 2021 Zhaorun Chen, Liang Gong, Te Sun, Binhao Chen, Shenghan Xie, David Filliat, Natalia Díaz-Rodríguez

While the rapid progress of deep learning fuels end-to-end reinforcement learning (RL), direct application, especially in high-dimensional space like robotic scenarios still suffers from high sample efficiency.

reinforcement-learning Reinforcement Learning (RL) +1

Explainability in Deep Reinforcement Learning

no code implementations15 Aug 2020 Alexandre Heuillet, Fabien Couthouis, Natalia Díaz-Rodríguez

A large set of the explainable Artificial Intelligence (XAI) literature is emerging on feature relevance techniques to explain a deep neural network (DNN) output or explaining models that ingest image source data.

Explainable artificial intelligence Explainable Artificial Intelligence (XAI) +2

Should artificial agents ask for help in human-robot collaborative problem-solving?

no code implementations25 May 2020 Adrien Bennetot, Vicky Charisi, Natalia Díaz-Rodríguez

Transferring as fast as possible the functioning of our brain to artificial intelligence is an ambitious goal that would help advance the state of the art in AI and robotics.


Egoshots, an ego-vision life-logging dataset and semantic fidelity metric to evaluate diversity in image captioning models

2 code implementations26 Mar 2020 Pranav Agarwal, Alejandro Betancourt, Vana Panagiotou, Natalia Díaz-Rodríguez

In this paper, we attempt to show the biased nature of the currently existing image captioning models and present a new image captioning dataset, Egoshots, consisting of 978 real life images with no captions.

Image Captioning Object Recognition

DisCoRL: Continual Reinforcement Learning via Policy Distillation

no code implementations11 Jul 2019 René Traoré, Hugo Caselles-Dupré, Timothée Lesort, Te Sun, Guanghang Cai, Natalia Díaz-Rodríguez, David Filliat

In multi-task reinforcement learning there are two main challenges: at training time, the ability to learn different policies with a single model; at test time, inferring which of those policies applying without an external signal.

reinforcement-learning Reinforcement Learning (RL) +2

Continual Learning for Robotics: Definition, Framework, Learning Strategies, Opportunities and Challenges

no code implementations29 Jun 2019 Timothée Lesort, Vincenzo Lomonaco, Andrei Stoian, Davide Maltoni, David Filliat, Natalia Díaz-Rodríguez

An important challenge for machine learning is not necessarily finding solutions that work in the real world but rather finding stable algorithms that can learn in real world.

BIG-bench Machine Learning Continual Learning

Intelligent Drone Swarm for Search and Rescue Operations at Sea

no code implementations13 Nov 2018 Vincenzo Lomonaco, Angelo Trotta, Marta Ziosi, Juan de Dios Yáñez Ávila, Natalia Díaz-Rodríguez

In recent years, a rising numbers of people arrived in the European Union, traveling across the Mediterranean Sea or overland through Southeast Europe in what has been later named as the European migrant crisis.

Don't forget, there is more than forgetting: new metrics for Continual Learning

no code implementations31 Oct 2018 Natalia Díaz-Rodríguez, Vincenzo Lomonaco, David Filliat, Davide Maltoni

Continual learning consists of algorithms that learn from a stream of data/tasks continuously and adaptively thought time, enabling the incremental development of ever more complex knowledge and skills.

Continual Learning Transfer Learning

State Representation Learning for Control: An Overview

1 code implementation12 Feb 2018 Timothée Lesort, Natalia Díaz-Rodríguez, Jean-François Goudou, David Filliat

State representation learning (SRL) focuses on a particular kind of representation learning where learned features are in low dimension, evolve through time, and are influenced by actions of an agent.

Representation Learning

Unsupervised Understanding of Location and Illumination Changes in Egocentric Videos

1 code implementation30 Mar 2016 Alejandro Betancourt, Natalia Díaz-Rodríguez, Emilia Barakova, Lucio Marcenaro, Matthias Rauterberg, Carlo Regazzoni

Wearable cameras stand out as one of the most promising devices for the upcoming years, and as a consequence, the demand of computer algorithms to automatically understand the videos recorded with them is increasing quickly.

Hand Detection

Cannot find the paper you are looking for? You can Submit a new open access paper.