GraphStax is a startup company currently in stealth with an entirely new kind of engine that directly takes full advantage of both artificial intelligence and machine learning in neural and symbolic systems.. We are a team of 12 today and we will soon unveil our achievements. Keep watching this site!
Neuro-Symbolic AI as quoted from Digital Trends: “For sure, deep learning has enabled amazing advances,” David Cox told Digital Trends. “At the same time, there are concerning cracks in the wall that are starting to show.” That makes them less good at statistically rare “black swan” problems. A black swan event, popularized by Nassim Nicholas Taleb, is a corner case that is statistically rare.
Our product, to be soon released upon maturation, early next year, is called Semantic Radar. Just like Radar is used in the physical world to sense, characterize, track and profile entities, their relationships, activities and behaviors for assessments, our new Semantic Radar does exactly this for the cyber domain.
We provide an illustration below to summarize the overview of our approach: combining the best of both the learning capabilities of quantum graph theory integrated with graph convolutional neural networks and symbolic representations we have applied this successfully in proving out the concepts that demonstrate a scalable and dramatic increase in quality, fidelity, accuracy and precision of predictions using the ROC/AUC metrics (Receiver Operating Characteristics & Area Under the Curve):