Project description
Extending deep learning to the meta level
Deep learning is a subset of machine learning that teaches computers to draw conclusions as humans would by continually analysing data. The field has led to remarkable progress in computer vision, speech recognition, natural language processing and reinforcement learning. The EU-funded DeepLearning 2.0 project aims to take deep learning to the next level. It will propose metal-level learning methods that improve the results and performance of learning algorithms. The new methods will help create novel, customised deep learning pipelines with no handcrafted elements, which will be more accurate, simpler to use and require less time to train. To demonstrate the viability of the proposed methods, researchers will implement the new customised deep learning pipelines to electroencephalography decoding and RNA folding.
Objective
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.
Fields of science
Programme(s)
- HORIZON.1.1 - European Research Council (ERC) Main Programme
Funding Scheme
HORIZON-AG - HORIZON Action Grant Budget-BasedHost institution
79098 Freiburg
Germany