[nickpsecurity]

People wanting this would be better off using memory architectures, like how the brain does it. For ML, the simplest approach is putting in memory layers with content-addressible schemes. I have a few links on prototypes in this comment:

https://news.ycombinator.com/item?id=42824960

[HarHarVeryFunny]

Animal brains do not separate long term memory and processing - they are one and the same thing - columnar neural assemblies in the cortex that have learnt to recognize repeated patterns, and in turn activate others.