Descripción del proyecto
Llevar el aprendizaje profundo a la metaescala
El aprendizaje profundo es una subdisciplina del aprendizaje automático que enseña a los ordenadores a sacar conclusiones de la misma manera que lo haría una persona a través del análisis continuo de datos. Esta subdisciplina ha favorecido un progreso notable en la visión artificial, el reconocimiento de voz, el procesamiento del lenguaje natural y el aprendizaje por refuerzo. El objetivo del proyecto DeepLearning 2.0 financiado con fondos europeos, es llevar el aprendizaje profundo al siguiente nivel. Propondrá métodos de aprendizaje a metaescala que mejoren los resultados y el rendimiento de los algoritmos de aprendizaje. Los nuevos métodos ayudarán a crear procesos de aprendizaje profundo novedosos y personalizados sin elementos manuales, que serán más precisos, más fáciles de usar y que requerirán menos tiempo de entrenamiento. Para demostrar la viabilidad de los métodos propuestos, los investigadores aplicarán los nuevos procesos de aprendizaje profundo personalizados a la descodificación de electroencefalogramas y al plegamiento del ARN.
Objetivo
Deep learning has revolutionized many fields, such as computer vision, speech recognition, natural language processing, and reinforcement learning. This success is based on replacing domain-specific hand-crafted features with features that are learned for the particular task at hand. The logical step to take deep learning to the next level is to also (meta-)learn other hand-crafted elements of the deep learning pipeline. We therefore propose to develop meta-level learning methods for the creation of novel customized deep learning pipelines, by means of:
1. Hierarchical neural architecture searchfor learning qualitatively new architectures and architectural building blocks from scratch;
2. Learning of optimizers and hyperparameter adaptation policies that adapt totheir context in order to converge faster and more robustly;
3. Learning the data to train on, to remove the need for large sets of labelled data; and
4. Bootstrapping from prior design efforts to increase efficiency and make an integrative design of architectures, optimizers, hyperparameter adaptation policies, and pretraining tasks feasible in practice.
These advances will allow the next generation of deep learning pipelines to achieve higher accuracy, lower training time, and improved ease-of-use (democratization of deeplearning). They will also allow a customization to particular design contexts, including additional objectives next to accuracy (such as robustness, memory requirements, energy consumption, latency, interpretability, training cost, uncertainty estimation, and algorithmic fairness) in order to facilitate trustworthy AI. In order to demonstrate the effectiveness of these methods, we plan to develop:
5. New state-of-the-art customized deep learning pipelines for various applications, including EEG decoding, RNA folding, and improving the reinforcement learning pipeline and deep learning on tabular data.
Ámbito científico
Programa(s)
- HORIZON.1.1 - European Research Council (ERC) Main Programme
Régimen de financiación
HORIZON-AG - HORIZON Action Grant Budget-BasedInstitución de acogida
79098 Freiburg
Alemania