Descripción del proyecto
Emplear el álgebra abstracta para lograr una inteligencia artificial más transparente
El aprendizaje automático algebraico es una técnica de aprendizaje automático relativamente nueva basada en representaciones algebraicas de datos. A diferencia del aprendizaje estadístico, los algoritmos de aprendizaje automático algebraico son robustos con respecto a las propiedades estadísticas de los datos y carecen de parámetros. El objetivo del proyecto financiado con fondos europeos ALMA es capitalizar las propiedades del aprendizaje automático algebraico para desarrollar una nueva generación de sistemas interactivos de aprendizaje automático centrado en el ser humano. Se espera que estos sistemas reduzcan los sesgos y eviten la discriminación, recuerden lo que saben cuando se les enseñe algo nuevo, favorezcan la confianza y la fiabilidad e integren restricciones éticas complejas en los sistemas de inteligencia artificial centrada en el ser humano. Además, podrían promover el aprendizaje distribuido y colaborativo.
Objetivo
Algebraic Machine Learning (AML) has recently been proposed as new learning paradigm that builds upon Abstract Algebra, Model Theory. Unlike other popular learning algorithms, AML is not a statistical method, but it produces generalizing models from semantic embeddings of data into discrete algebraic structures, with the following properties:
P1: Is far less sensitive to the statistical characteristics of the training data and does not fit (or even use) parameters
P2: Has the potential to seamlessly integrate unstructured and complex information contained in training data, with a formal representation of human knowledge and requirements;
P3. Uses internal representations based on discrete sets and graphs, offering a good starting point for generating human understandable, descriptions of what, why and how has been learned
P4. Can be implemented in a distributed way that avoids centralized, privacy-invasive collections of large data sets in favor of a collaboration of many local learners at the level of learned partial representations.
The aim of the project is to leverage the above properties of AML for a new generation of Interactive, Human-Centric Machine Learning systems., that will:
- Reduce bias and prevent discrimination by reducing dependence on statistical properties of training data (P1), integrating human knowledge with constraints (P2), and exploring the how and why of the learning process (P3)
- Facilitate trust and reliability by respecting ‘hard’ human-defined constraints in the learning process (P2) and enhancing explainability of the learning process (P3)
- Integrate complex ethical constraints into Human-AI systems by going beyond basic bias and discrimination prevention (P2) to interactively shaping the ethics related to the learning process between humans and the AI system (P3)
- Facilitate a new distributed, incremental collaborative learning method by going beyond the dominant off-line and centralized data processing approach (P4)
Ámbito científico
- natural sciencesmathematicspure mathematicsdiscrete mathematicsmathematical logic
- social sciencessociologysocial issuessocial inequalities
- natural sciencesmathematicspure mathematicsalgebra
- natural sciencescomputer and information sciencesartificial intelligencemachine learning
- natural sciencescomputer and information sciencesdata sciencedata processing
Palabras clave
Programa(s)
Convocatoria de propuestas
Consulte otros proyectos de esta convocatoriaConvocatoria de subcontratación
H2020-EIC-FETPROACT-2019
Régimen de financiación
RIA - Research and Innovation actionCoordinador
28760 TRES CANTOS MADRID
España
Organización definida por ella misma como pequeña y mediana empresa (pyme) en el momento de la firma del acuerdo de subvención.