Current Applications

The development of new applications requires the definition of Input Neurons (sensor neurons / motor neurons) and a definition for linking these together based on temporal or spatial characteristics. A distinct NeuraBASE™ model can then be built to represent multiple levels of data e.g. bits to characters, characters to words, words to phrases etc.

Bioinformatics
SynaBASE is a novel database platform which finds and stores “patterns” rather than fixed length indices that allow computationally demanding analyses such as data from next generation sequencers and large scale comparative genomics to be completed 100s of times faster. Redundant patterns from new data are not stored, resulting in improvements in database scalability. This technology allows genomics laboratories and researchers worldwide to manage their data effectively, increasing analytical productivity while providing significant savings on data storage. A large number of SynaBASE-powered applications have been developed based upon internal research as well as in collaboration with some of the world’s leading genomics and bioinformatics researchers. 

Real-time Translation
LinguaBASE is a high-throughput natural language processing engine that enables the real-time translation of human languages at extreme throughputs. The development of a new translation system involves the use of LinguaBASE to autonomously mine parallel corpora for phrases that share semantic similarities. These phrases represent concepts shared between languages, with each corpora representing a concept map of a particular language. Translation becomes possible through the mapping of the new language concepts to concepts for existing languages. By avoiding the need to program linguistic rules for each pair of languages, LinguaBASE-powered translation systems are able to offer throughputs up to 500,000 words per minute per server.