THE CORE TECHNOLOGY
The core technology of Neural Concept Shape is based on 3D convolutional networks that learn to predict the output of physical simulations or experiments based on the input shape's geometrical properties.
ABOUT SHAPE EXPERT
Although deep learning has taken the entire field of computer science by storm, Computer Assisted Design (CAD) and geometry processing still mostly rely on traditional techniques.Learn more
Train your AI once and use it forever
- Transfer learning between projects and programs.
- Exploit simulation and test data jointly.
Accuracy is key
- Our geometric Neural Networks operate in the Euclidean and physical space, and naturally learn the patterns of flows and structures.
- Shape Expert is made to analyze and optimize the performance of your models before use.
Works with your everyday files
- Geometries: lges, step, stl, catpart, etc.
- Simulation results in all common formats.
FOR ADVANCED EXPERTS
The power of deep learning rethought for advanced CAE or optimization experts.
BENEFITS OF SHAPE EXPERT
Low-level Python-based interface that lets you interact with the core technology and removes any limitations.
A fully guided workflow that helps you start with the best practices right away.
Generative neural networks taken out of the lab, optimized and made ready to work.
HOW DOES IT WORK?
Building a successful market expansion: new collaboration between Neural Concept & CYBERNET (Japan)
Neural Concept raises a $9.1m Series A to scale Engineering Intelligence within industrial organizations
Mubea using Neural Concept Shape for the Design of Innovative Lightweight Components
Optimo Medical AG Accelerates Patient-specific Surgery Planning By 100 Times, thanks to Neural Concept
With additional funding raised and a new advisory board, Neural Concept is getting ready for a strong 2021
When CAE meets Deep Learning: Personal Experience sharing on a Game Changer for Engineering Processes
NUMECA uses Neural Concept’s Deep Learning Platform to Study the Nature of Turbulence
Neural Concept SA and EPFL CVLab at NeurIPS 2020: “MeshSDF: Differentiable Iso-Surface Extraction.”
Deep Learning-based Models for Fast Evaluations of Airfoil Performances in Transonic Flows
In the Quest for Breaking the World Record: Collaboration with SP80 to Optimize Ventilated Hydrofoils Profiles
Miniswys uses Neural Concept Shape for the Design Optimization of Customized Ultrasonic Actuators