Meta AI Chief Yann LeCun has published a paper that describes a lack of ‘common sense’ in current AI efforts. The paper lays out a pathway to future iterations that ‘learn as efficiently as humans and animals’ as they become increasingly autonomous. Common sense is a collection of’models of the world’ that allow humans to predict whether events are likely or unlikely, plausible or implausible, and possible or impossible’ LeCUN proposes retooling algorithm training methodology to learn more efficiently and thus develop a composite of the common sense we humans take for granted. The Meta AI chief’s next generation algorithm-training architecture involves a bunch of moving parts such as a system that replicates short-term memory, another that teaches neural networks self-criticism. . . .
Read more at futurism.com