for - semantic fingerprint - semantic space - semantic folding - cortical.io

for - semantic folding - semantic fingerprint - cortical.io - numenta - sparse coding - Francisco Webber - symmathesetic fingerprint

summary - In this informative interview, Francisco Webber, a principal cofounder of Cortical.io, discusses how the company's core technology, semantic folding and semantic fingerprints of words is unique and differs from the usual AI large language models. - Cortical I/O's approach is a biomimicry approach that is based on representing words in the way that brain operates. - It employs a word-to-geometry mapping implemented using Numenta's sparse coding technique. - This approach allows Cortical to train using very small training data sets of 100 gigabytes of data, which takes a few hours to train - many orders of magnitudes smaller than normal AI training data sets.

for - semantic folding - semantic fingerprint - natural language processing - NLP - cortical.io - Numenta