As weapon systems and fleets become more complex and inter-connected, the number of anomalies that one can face increases rapidly. The problem lies in the fact that:
In highly complex systems the number of potential anomalies can be astronomical.
It is impossible to learn to recognize them all. Besides, systems evolve over time, which means that it may be necessary to continue re-learning old lessons to keep up with the constant changes. This can be very costly, not to say impractical. And quite difficult if someone is, say, firing missiles at you.
Our QCM technology offers a radically innovative alternative to conventional anomaly detection based on Machine Learning. We know (from experience) that when ‘strange things’ happen in complex systems (but not only in complex systems) it is because under the surface a lot of physics is taking place. There are many things that are known that can go wrong, but there also as many that we still haven’t seen:
Machine Learning is often impractical because there are many anomalies that are unknown.
Our Quantitative Complexity Management (QCM) technology is a new form of Artificial Intelligence that reaches beyond the conventional Machine Learning (ML) approach. The main problem with Machine Learning is that it requires numerous examples in order to recognize and classify patterns. While this works well when it comes to recognizing a face or handwriting, in the case of expensive and complex military hardware it is impractical. The fact is that there are not enough anomalies to learn from. Such anomalies can be hugely expensive and nobody – manufacturers or users – can provide a sufficient number of cases from which to learn. Besides, the number of possible anomalies is immense and it is impossible to define and learn to recognize them.
QCM is Artificial Intuition
The key feature of QCM technology is that it is able to recognize the existence of anomalies the first and only time it is confronted with them. It is also able to pinpoint their sources thanks to a technique known as Complexity Profiling. This capability is particularly attractive as it functions independently of the fact that a particular piece of hardware or system is upgraded, modified, or even damaged during a mission. In all such cases ML would not work as one would need to train it anew each time a given system undergoes changes.
QCM, on the other hand, is like human intuition, like instinct. Anyone can feel that something is wrong by listening to a running engine which produces a strange sound without being a trained mechanic.
QCM is Artificial Intuition
With QCM we Find Anomalies you don’t even know you have.
Machine Learning can’t do this.
During years of testing on armoured vehicles, QCM has been shown to not only anticipate anomalies, before they become visible, it can also find anomalies in new vehicles that Quality Control missed.
We have a hardware solution that does all of this in real-time, onboard a vehicle, with no need to transmit data, thereby guaranteeing a high degree of security. It is called the CAHMS:
We anticipate anomalies, onboard, in real time, with no data transmission.
Read more here on Artificial Intuition.
Interested? Email us at email@example.com
0 comments on “Artificial Intuition Finds Unknown Anomalies – Beyond Machine Learning”