CORDIS
EU research results

CORDIS

English EN
A Theory for Understanding, Designing, and Training Deep Learning Systems

A Theory for Understanding, Designing, and Training Deep Learning Systems

Objective

The rise of deep learning, in the form of artificial neural networks, has been the most dramatic and important development in machine learning over the past decade. Much more than a merely academic topic, deep learning is currently being widely adopted in industry, placed inside commercial products, and is expected to play a key role in anticipated technological leaps such as autonomous driving and general-purpose artificial intelligence. However, our scientific understanding of deep learning is woefully incomplete. Most methods to design and train these systems are based on rules-of-thumb and heuristics, and there is a drastic theory-practice gap in our understanding of why these systems work in practice. We believe this poses a significant risk to the long-term health of the field, as well as an obstacle to widening the applicability of deep learning beyond what has been achieved with current methods.

Our goal is to tackle head-on this important problem, and develop principled tools for understanding, designing, and training deep learning systems, based on rigorous theoretical results.

Our approach is to focus on three inter-related sources of performance losses in neural networks learning: Their optimization error (that is, how to train a given network in a computationally efficient manner); their estimation error (how to ensure that training a network on a finite training set will ensure good performance on future examples); and their approximation error (how architectural choices of the networks affect the type of functions they can compute). For each of these problems, we show how recent advances allow us to effectively approach them, and describe concrete preliminary results and ideas, which will serve as starting points and indicate the feasibility of this challenging project.
Leaflet | Map data © OpenStreetMap contributors, Credit: EC-GISCO, © EuroGeographics for the administrative boundaries

Host institution

WEIZMANN INSTITUTE OF SCIENCE LTD

Address

Herzl Street 234
7610001 Rehovot

Israel

Activity type

Higher or Secondary Education Establishments

EU Contribution

€ 1 442 360

Beneficiaries (1)

Sort alphabetically

Sort by EU Contribution

Expand all

WEIZMANN INSTITUTE OF SCIENCE LTD

Israel

EU Contribution

€ 1 442 360

Project information

Grant agreement ID: 754705

Status

Ongoing project

  • Start date

    1 September 2018

  • End date

    31 August 2023

Funded under:

H2020-EU.1.1.

  • Overall budget:

    € 1 442 360

  • EU contribution

    € 1 442 360

Hosted by:

WEIZMANN INSTITUTE OF SCIENCE LTD

Israel