A Look Behind the Scene

Similar to the human brain, the Q-Engine is powered by components that are continuously learning, communicating and adapting to form a single unit that's robust in the face of surprise.  The engine is constantly making prediction about future events and comparing that with the actual outcome to improve on its predictions. After the system has accomplished a task through the "Intelligent Behavior" module, it evaluates it's accuracy and transmits back the need (when necessary) for more relevant data sources. 

QOPIUS ENGINE CHARACTERISTICS

ARTIFICIAL MOTIVATION AND CURIOSITY 

The Qopius Engine has the ability to discover by itself the objectives that will accelerate its development. 

 

PLASTICITY

The integration of new knowledge is done so that it does not disturb the existing one. The importance of each informational stream is constantly influences and weighted depending on their likelihood and usefulness. The Qopius engine has the ability to select modalities that give high performances at a time and inhibit the others.


VIGILANCE

The Engine always tries to predict the next information it will receive. Mis-predicted information receive high attention from the engine and lead to curiosity and learning.

TRANSPARENCY 

The structure of the engine has been imagined so that we can follow (and potentially influence) the development of the artificial intelligence. 

 


THE TECHNIQUES

A few of the techniques behind the engine include deep learning, evolutionary algorithms and decision tree learning

deep_network_illus.jpg

DEEP LEARNING

 
algorithmia-ft1.jpg

EVOLUTIONARY ALGORITHMS

  • Search Optimal Parameters in high dimensional space

  • Multimodal integration fusion of different sources

  • Combining models and functions

 

Contact us to learn more on how these techniques are put in action