2020 BRN Discussion, page-13612

all the dogs are doing is detecting volatile organic compounds and that is EXACTLY what brainchip are doing with Akida ..

The paper was merely a proof of concept test. Akida was using a prepared data set consisting of just 20 compounds. It was published in a junk journal from notorious Chinese company MDPI. The paper has zero citations.
https://scholarlyoa.com/more-pseudo-science-from-swiss-chinese-publisher-mdpi/

Real world odour detetion typically involves weighting thousands of different volatiles (from potentially millions) and processing the data in real time. That is arguably billions of times harder.

"Based on results obtained using a benchmark dataset, the model achieved a high classification accuracy for a large number of odors and has the capacity for incremental learning on new data. "

"Further directions in the brain-inspired study of odor machine classification include investigation of more biologically plausible algorithms for mapping, learning, and interpretation of odor data along with the realization of these algorithms on some highly parallel and low power consuming neuromorphic hardware devices for real-world applications."