About us

LAST NEWS:  EU is supporting DigiTwins (digital twin for health). ADAGOS plays the role of technology provider in the project. For more information see the DigiTwins Press Release.

ADAGOS products are integrated into Deep Quantitative Learner framework.

Deep Quantitative Learner in Q&A

  • Why would I need it?
    • Our products create the Digital Twin of your system from operational data.
      You can test your ideas on the digital copy before applying only the best one to the real system.
  • Why quantitative?
    • Our solutions learn real-world physics and system behavior.
    • We work with the following applications:
      • Long-term prediction with dynamical systems
      • Nonlinear compression
      • Complex phenomena learning
  • Why deep?
    • Construction of the models for the considered applications requires a large number of neural network layers

Typical network architecture

  • What is new and what is better?
    • Quantitative + Deep = Fundamental issues in learning.
    • We create new learning methods from scratch. These methods are able to cope efficiently with the issues raised.
Learning algorithms Arithmetic
Classical AI Slow convergence is acceptable 32 bits is enough
Quantitative approaches Classical powerful methods are critically failing 64 bits is far from being enough

Fields of applications

System control

– New command laws, based on our long-term prediction tools           – Effective robust control

Reliability and security

– Mechanical fatigue assessment                         – Uncertainty quantification

Decision support

– Development of patient specific models for medical          applications                        – Risk assessment

Production and maintenance optimization

– Preventive maintenance                   – Planning models


Topologically optimized neural network (focus on your core business)
Learning physics and complex system behavior from data
Mastering of dynamic and nonlinear behavior

Deep quantitative learner framework


deepROM® is our neural network factory. It excels at figuring out automatically the optimal network topology. The whole process is then standalone and avoids overlearning. Hence the user only has to provide the learning data and shortly after gets a reliable model. See examples here.


xROM™ is our implementation of recurrent reduced order models. It builds models for nonlinear dynamic processes and get rid of their inherent instabilities. See examples here.


zROM® (for adaptively generated simulation data) is a nonintrusive tool that builds a reduced order model of the frequency response of a system from learning data. zROM® controls adaptively the data generation process.  See an example in the field of mechanics.


Our convolutional neural network solution is adapted to higher dimensional problems. It gets rid of the so-called curse of dimensionality. It controls adaptively the data generation process. See examples here.


AdagosOpt™ is our optimization tool based on reduced order modeling. It is suitable for strongly nonlinear behavior and for quantitative or qualitative discrete variables. It controls adaptively the data generation process. See an application to telecomSee an application to the design of a power plant.


AdagosFit™ is a hierarchical learning process whose aim is to model high dimensional functions. It controls adaptively the generation, by a solver, of learning data.

Our partners

What our clients say

En rupture totale par rapport à l’état de l’art, la société ADAGOS arrive à créer des modèles réduits ayant un grand nombre de paramètres (plusieurs centaines dans les cas considérés). Cela veut dire que ces outils ne semblent pas être affectés par ce que l’on appelle la malédiction de la dimension (curse of dimensionality). Cela parait d’autant plus étonnant que nos paramètres varient dans des intervalles très larges et ont un caractère discret aussi bien qualitatif que quantitatif.

Jean-Marie Hamy Technical Project Manager and Design Authority @ AREVA NP

Les enjeux sont considérables pour les systèmes embarqués et les applications médicales. De ce fait, nous maintenons une veille technologique et nous sommes en contact avec les universités les plus prestigieuses pour scruter la moindre évolution dans le domaine. Mais, il n’était pas nécessaire d’aller chercher bien loin, l’innovation de rupture peut venir d’une petite startup toulousaine appelée ADAGOS.

Michel Rochette Director of research @ Ansys France

Our team

9 avenue de l'Europe - 31520 Ramonville-Saint-Agne