An Artificial Intelligence algorithmic platform
to help the engineer achieve more

How does it work?

The core technology of Neural Concept shape are 3D convolutional networks that learn to predict the output of physical simulations or experiments based on the input shape’s geometrical properties. They can be used as complements to the traditional numerical simulation and experimental methods so as to alleviate the need for actual simulations or experiments along the conception pipeline. This dramatically accelerates and reduces the cost of the design process.

This proprietary deep learning technology is also fully integrated with state-of-the-art shape optimisation algorithms. Therefore, when relevant, the conception process can even be completely automated so as to find the optimal design(s) given a number of predefined objectives.

Case studies

Satellites: A smarter design regarding the thermal constraints

Formula 1: Multiple connected components and long-range aerodynamic correlations

Volumetric field predictions: A benchmark using Neural Concept Shape

Multi-fidelity optimization of a fixed-wing drone using Geometric Convolutional Neural Networks

Hydrofoil: Fly faster, longer, safer

Speed Bicycle: Our optimized aero-bike broke two world records!


EPFL Innovation Park, Batiment C, 1015 Lausanne


Landshuter Allee 8-10,
80637 München

Pin It on Pinterest