Skip to main content
Go to the home page of the European Commission (opens in new window)
English en
CORDIS - EU research results
CORDIS

ODD-ML: Out-of-Distribution Deployable Machine Learning

Project description

Rethinking how AI adapts to the real world

Machine learning powers everything from medical diagnostics to climate models. However, moving from the lab to the real world is not easy. Data shifts, unforeseen conditions, and human complexity can challenge even the best algorithms. The ERC-funded ODD-ML project aims to solve this problem by putting people back at the centre of machine learning. Instead of relying solely on past data, ODD-ML will design AI systems that actively learn from human experts. Specifically, the machines will capture human intuition, experience, and even biases. By bridging human insight and machine reasoning, the project seeks to create AI that adapts more intelligently to new situations, boosting trust, reliability, and real-world impact.

Objective

ODD-ML addresses the open secret of machine learning (ML), which is that model deployment often fails. The problem arises because deployment contexts may differ from the data used to train ML models in unexpected ways. In an increasingly data-driven era, this severely impedes progress in ML-powered R&D and our ability to tackle societal grand challenges with existing ML tools.

To solve this pervasive issue, I propose a radical alternative to current ML approaches, placing human experts at the core of iterative design-build-test-learn (DBTL) loops. My approach comprises the interlinked steps of re-conceptualizing the deployment issue as a need for active learning from domain experts and other indirect sources and, to succeed here, recognizing the imperfect and often tacit knowledge and limited time of human experts, designing ML systems that can rapidly reverse-engineer expert knowledge.

I will achieve this with a combination of ideas transformative for human-AI collaboration: human inductive biases will be inferred from computational-rationality-based cognitive models, amortized on pre-computed solutions for speed, allowing interactive online use. I envision widespread impact in ML, on complex decision-making, and broadly across R&D domains.

Fields of science (EuroSciVoc)

Programme(s)

Topic(s)

Funding Scheme

HORIZON-ERC - HORIZON ERC Grants

See all projects funded under this funding scheme

Call for proposal

(opens in new window) ERC-2024-ADG

See all projects funded under this call

Host institution

AALTO KORKEAKOULUSAATIO SR
Net EU contribution
€ 2 495 282,00
Address
OTAKAARI 1
02150 Espoo
Finland
Region
Manner-Suomi Helsinki-Uusimaa Helsinki-Uusimaa
Activity type
Higher or Secondary Education Establishments
Links
Total cost
No data

Beneficiaries (1)