"Neural networks (at least in the configurations that have been dominant over the last three decades) have trouble generalizing beyond the multidimensional space that surrounds their training examples. That limits their ability to reason and plan reliably."
But humans also have this limitation. Every science discovery is just some new data we can train on and create models for, both mentally and mathematically.
But humans also have this limitation. Every science discovery is just some new data we can train on and create models for, both mentally and mathematically.