Neuro-Symbolic AI

The Neuro-symbolic AI Group aims at developing models which are capable of complex, transparent, data-efficient and safe inference.

We operate at the interface between neural and symbolic AI methods aiming to enable the next generation of explainable, data-efficient and safe AI systems. Our research investigates how the combination of latent and explicit data representation paradigms can deliver better learning and reasoning over data.

The group is part of Idiap’s Cross Research Groups (CRGs) initiative, aiming to promote strategic areas in AI and to facilitate internal integration across research groups, external collaborations and industrial applications.

Neuro-symbolic AI methods are critical to enable the application of AI methods in industrial settings, facilitating the development of models which are transparent, safe and that can generalise over small and heterogeneous datasets.

Our current research areas include:

General Areas

Natural Language Processing
Neuro-symbolic AI
Interpretable/Explainable AI

Natural language inferenc

Abductive inference
Mathematical Language processing
Explanation generation
Explainable question answering
Scientific inference & explanations

Neuro-symbolic models

Multi-hop reasoning
Semantic & inference controls
Conceptual & Knowledge representation in NLP
Graph models in NLP
Disentanglement in NLP
Safe NLP

AI applications in Biomedicine

Biologically-informed models
Hybrid Mechanistic-statistical models
Clinical decision support
NLP for supporting drug discovery
Clinical trial design

Group News

Perspectives on AI Symposiums

research — last modified Jun 02, 2023

Beyond deep learning: Learning from small and heterogeneous data

New Cross Research Group to address societal challenges

research — Mar 16, 2023

Created in 2022, Cross Research Groups will foster collaborations between Idiap research groups. Their aim is to have long-term impacts on society thanks to an approach mixing both business oriented solutions and interdisciplinary scientific groundwork.

A partnership to accelerate antibiotic research

tech — Oct 05, 2022

Accelerating the selection of potential sources of antibiotics using artificial intelligence is one of the goals of ABRoad. This project is the result of a partnership between InflamAlps, a pharmaceutical R&D company, and Idiap. Supported by The Ark Foundation, this innovative project aims to develop a digital platform enabling the selection of potential sources of antibiotics.

Idiap is looking for its next director

institute — Jan 14, 2022

Idiap Research Institute and the School of Engineering at EPFL invite applications for the directorship of Idiap. The successful candidate will also hold a faculty position as full professor at EPFL School of Engineering.

Four new researchers join the effort to shape the future of AI

institute — Feb 26, 2021

Idiap is developing its research capacities by hiring four new senior researchers. Two women and two men, whose goal will be to work on topics with great potential in AI and to continue to progress in areas that have already contributed to the reputation of the institute.

More News

Group Job Openings

Our group is regularly posting job openings ranging from internships to researcher positions. To check the opportunities currently available or to submit a speculative applications use the link below.Our group is regularly posting job openings ranging from internships to researcher positions. To check the opportunities currently available or to submit a speculative applications use the link below.

Other jobs