Neural Concept : The first 3D Deep Learning dedicated to CAE

Neural Concept offers the first-ever deep learning-based software solution dedicated to Computer-Assisted Engineering and Design. It speeds up R&D cycles, enhances product performance, and reduces simulation costs. The software allows the engineer to extract maximum value from simulation data, allowing him to explore an infinite number of designs without calling back the expensive simulator and to automatically optimize a shape given a set of performance goals.

Their software searches the space of shapes to find the best compromise while saving the engineer time, energy and economic cost. Neural Concept Shape is a force multiplier that will make it possible to test several orders of magnitude more variations of a given design than what is currently possible. This will result in far more optimized shapes and potentially, to solutions that a human designer may not have previously considered.

Their solution is completely “data-driven”, and does not require any parametrization of the shape. NCS is particularly suited for highly complex systems, such as multiphysics simulations since it encapsulates most of the complexity within the learning process and offers engineers a simplified interface to interact with the physical system.

Neural Concept is a spin-off from EPFL, from the Computer Vision Lab of Professor Pascal Fua. It is the result of a software package developed at EPFL’s computer vision laboratory over the last 3 years.

The company was founded in May 2018. At the time of the foundation, several industrials had already expressed their strong interest in the technology and this is what motivated the creation of a commercial entity.

Pierre Baqué is the CEO of the company and main shareholder of Neural Concept and he co-founded the company with Pascal Fleuret, a Senior Scientist at Idiap, head of the machine learning group and professor at EPFL and Pascal Fua, professor at EPFL’s Computer Vision Lab and founder of PlayfulVision and Pix4D. He has strong business development and marketing experience since he co‐founded a leading software for optimization in the ropeways engineering industry and developed AI‐based trading tools in Credit‐Suisse Investment Bank.

Pierre received an engineering degree in Applied Mathematics and a Masters degree in Operations Research from Ecole Polytechnique, in 2013. After working as an Engineer for Credit-Suisse in London, he joined the Computer Vision Laboratory at Ecole Polytechnique Fédérale de Lausanne. He got the doctoral degree in early 2018 under the supervision of Prof. Pascual Fua and Francois Fleuret. His research focused on Deep Structured Learning and Variational Inference applied to Computer Vision. As a result of his doctoral thesis, Pierre took the leap as an entrepreneur and founded Neural Concept in 2018, through which he has acquired important business and commercial knowledge.

François Fleuret received the Ph.D. degree in Mathematics from the University of Paris VI in 2000, and a habilitation degree in Mathematics from the University of Paris XIII in 2006. He is the head of the Machine Learning group at the Idiap Research Institute, Switzerland. Prior to that, he held positions at the University of Chicago, USA, at the Institut de Recherche en Informatique et en Automatique (INRIA), France, and at the École Polytechnique Fédérale de Lausanne (EPFL), Switzerland. He serves as Associate Editor of the IEEE Transactions on Pattern Analysis and Machine Intelligence and is an expert for several European funding agencies.

Pascal Fua received an engineering degree from Ecole Polytechnique, Paris, in 1984 and a Ph.D. degree in Computer Science from the University of Orsay in 1989. He then worked at SRI International and INRIA Sophia-Antipolis as a Computer Scientist. He joined EPFL in 1996 where he is now a Professor in the School of Computer and Communication Science and heads the Computer Vision Laboratory.

His research interests include shape modeling and motion recovery from images, analysis of microscopy images, and Augmented Reality.  He has (co)authored over 300 publications in refereed journals and conferences. He is an IEEE Fellow and has been an Associate Editor of IEEE journal Transactions for Pattern Analysis and Machine Intelligence. He often serves as a program committee member, area chair, and program chair of major vision conferences and has cofounded two spinoff companies (Pix4D and PlayfulVision).

Neural Concept is working with major actors of the Aerospace, Automotive, Naval and Additive Manufacturing industries. After having conducted several pilots studies, we are selling direct licenses to our clients, on premise or on cloud. The conversion rate is very good as most of our clients are convinced and adopt our technology after the first trial. Said Founder.

They are releasing within the next weeks a Cloud version that will be available to a larger audience. In the meantime, working on reaching other major industries. On the news side, they designed an aero-bike which recently broke two world records of speed! It was the first bike designed entirely by the software, without any human intervention.

Message from the Founders

We build a tool made to accelerate your design processes. We are allowing you to make rational design choices and to make the most out of the data that you already have. You can try a free demo on our website. where there is also more about the use cases that are publicly shared and the first description of our technology. Do not hesitate to reach us, we would be glad to know how our technology could help you to achieve more!