Image recognition: the promise of a new approach to energy-efficient AI

To com­mu­nic­ate with oth­er cells, such as those in muscles and vari­ous glands, neur­ons emit elec­tric­al sig­nals.

The amp­litude of each of these elec­tric­al sig­nals is approx­im­ately 100 mil­li­volts; a read­ing that remains con­stant regard­less of the neur­on or the inform­a­tion.

“But elec­tric­al sig­nals are extremely rare,” says Simon Thorpe.

“Indeed, mod­els based on stat­ist­ic­al sci­ence were then con­sidered to have a lower mar­gin of error than those based on neur­os­cience,” explains Jean-Gab­ri­el Ganascia.

exclaims Simon Thorpe.