Inspired by the latest findings on the way the brain processes information, Cortical.io’s Retina Engine converts language into semantic fingerprints, a numerical representation that captures meaning explicitly and operates on it computationally.
The Retina Engine compares the semantic relatedness of any two texts by measuring the overlap of their fingerprints. It can be easily customized for any language, domain or jargon and delivers results quickly, at low costs.
The intrinsic difference of Cortical.io’s algorithm makes it possible to solve many open NLU challenges like meaning-based filtering of terabytes of unstructured text data, real-time topic detection in social media or semantic search over millions of documents across languages.
The company was founded in 2011 and holds a broad general license for Numenta’s HTM technology. Cortical.io has offices in Vienna, Austria, New York and the San Francisco Bay Area.
We are active members of the NuPIC (Numenta Platform for Intelligent Computing) community, an open-source project that makes the Hierarchical Temporal Memory (HTM) available to software developers. HTM is an online learning system modeled on how the neocortex performs tasks such as visual pattern recognition and understanding spoken language.
Unlike traditional computer systems, it does not require conventional training and testing of data sets. Like the brain, the HTM uses SDRs to store information.
In May 2015, we entered a strategic partnership with Numenta, that grants us a broad general license to the HTM technology. Combined with our Semantic folding technology, it will enable us to apply our approach to applications like sentiment analysis, automatic summarization, semantic search, and conversational dialogue systems.Read this press release