ADAGOS introduces NeurEco©, the third neural networks generation

NeurEco creates parsimonious neural networks
It puts an end to the oversized second generation neural networks

NeurEco drastically reduces resources required for implementing AI
(energy consumption, development time, learning data)

NeurEco makes AI accessible
It can be used by experts and non-experts alike to open new horizons in deep learning

"Are you concerned by the carbon footprint of AI and want to reduce it?"
Help us to promote NeurEco

"Are you struggling to embed complex AI on small microcontrollers?"
NeurEco requires a fraction of the resources, compared to conventional AI

“Are you interested in AI, but hesitant to get started?"
You can dive straight into NeurEco without any prerequisite knowledge

"Are you an AI expert and want to be more efficient?"
NeurEco spectacularly reduces development time

"Is your business oriented to quantitative predictions (dynamic modelling, production management, …)?"
Discover new horizons of application of AI, opened by NeurEco

NeurEco: AI 4 all
  • Automatic neural networks creation
    • Requires no further development by user
    • Frees up their time to focus on your core tasks
  • Our algorithm takes charge of creating the optimal network
    • The final network is parsimonious, in contrast with oversized classical ones
    • Minimizes computational resources; energy consumption and carbon footprint are drastically reduced
  • Effective for both large and small sets of training data
    • Suitable for applications where training data is constrained
NeurEco: new horizons in AI
  • Accuracy
  • Continuous and discrete responses
  • Dynamic modelling
  • Interpretable models
  • Robustness against attacks
  • Incremental or continuous learning
Our parsimonious neural networks represent a major step forward from the state of the art.

A major industrial player put ADAGOS in competition with one of the world-leaders in AI on the problem of predicting turbocharger blade deflections. Without a doubt, the results were in our favor:

The world-leader’s network

ADAGOS’ parsimonious network

 

Leading Tech Compagny ADAGOS
Learning data
(Percentage of available data)		 1,000,000 samples
(100%)		 10,000 samples
(1%)
Size of the network (Number of links) 500,000 194
Computing resources A $ 15,000 GPU card 1 minute 13'' on a laptop

 

Other results of comparison with the state of the art are available here

Our customers

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 @ Framatome

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