A human fingerprint is the biological identity card of a single person. There are no two identical fingerprints, which makes them an ideal identification criterion. A semantic fingerprint is the identity card of a single concept. It characterizes in a unique, descriptive way the meanings associated with that concept.
Pictures and audio recordings are traditional semantic representations that capture different dimensions (visual, audio) of the same concept. You’ll see a picture of a jaguar or hear its growling and you’ll immediately know that you are looking/listening to a feline. But what about the word “jaguar”? Without the help of the context, there is no way to know whether the text is about felines or cars.
Our Semantic Fingerprinting method enables the creation of a unique semantic fingerprint for any word, any document, and in the near future even for any entity that can be described with natural language. The big difference to conventional semantic systems is that the conversion of words into their semantic fingerprints through cortical.io’s Retina is automated. There is no need for costly, time-consuming manual intervention anymore.
The invention of cortical.io’s Retina could revolutionize the search and analysis of text-based information, not only because of its transparency and simplicity of use, but also because of its small footprint: huge amounts of text –structured and unstructured- can be processed with moderate computational power.
That’s the kind of elementary semantic equations that cortical.io’s Retina can solve. And it enables a computer to answer the question “What does the fox eat?”, as demonstrated by Subutai Ahmad at the Numenta Hackathon in the fall of 2013.