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

Using deep learning to understand computations in neural circuits with Connectome-constrained Mechanistic Models

Project description

Combining machine learning with mechanistic modelling with deep learning

Advances in mapping neural circuits in organisms such as Drosophila melanogaster, the common fruit fly, raise the question of how to use these connectomes to understand neural computations and behaviour. Science requires models that align with both connectomes and biophysics. However, current mechanistic models cannot optimise for tasks, while deep learning models lack interpretability. The ERC-funded DeepCoMechTome project aims to design a machine learning framework that merges mechanistic modelling with deep learning. It will focus on two main neural computations in the fly by creating optimised models for the optic lobe and motor control circuits, to extract visual information and coordinate leg movements. This approach applies to different neural circuits and behaviours, resulting in hypotheses about neural tuning and enhancing experimental perturbations.

Objective

Advances in experimental techniques yield detailed wiring diagrams of neural circuits in model-systems such as the Drosophila melanogaster. How can we leverage these complex connectomes, together with targeted recordings and perturbations of neural activity, to understand how neuronal populations perform computations underlying behavior? Achieving a mechanistic understanding will require models that are consistent with connectomes and biophysical mechanisms, while also being capable of performing behaviorally relevant computations. Current models fail to address this need: Mechanistic models satisfy anatomical and biophysical constraints by design, but we lack methods for optimizing them to perform tasks. Conversely, deep learning models can be optimized to perform challenging tasks, but fall short on mechanistic interpretability.

To address this challenge, we will provide a machine learning framework that unifies mechanistic modeling and deep learning, and will make it possible to algorithmically identify models that link biophysical mechanisms, neural data, and behavior. We will use our approach to study two key neural computations in D. melanogaster. We will build large-scale mechanistic models of the optic lobe and motor control circuits which are constrained by connectomes and physiological measurements, and optimize them to solve specific computational tasks: Extracting behaviorally relevant information from the visual input, and coordinating leg movements to achieve robust locomotion. Our methodology for building, interpreting and updating these `deep mechanistic models' will be applicable to a wide range of neural circuits and behaviors. It will serve as a powerful hypothesis generator for predicting neural tuning and optimizing experimental perturbations, and will yield unprecedented insights into how connectivity shapes efficient neural computations in biological and artificial networks.

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-2022-COG

See all projects funded under this call

Host institution

EBERHARD KARLS UNIVERSITAET TUEBINGEN
Net EU contribution
€ 1 997 321,00
Address
GESCHWISTER-SCHOLL-PLATZ
72074 Tuebingen
Germany
Region
Baden-Württemberg Tübingen Tübingen, Landkreis
Activity type
Higher or Secondary Education Establishments
Links
Total cost
€ 1 997 321,00

Beneficiaries (1)