It is an amazing talk with a lot of inspirations. Indeed, we need to model the biology and simulate the system in our body, with which we may get a better understanding of diseases, thus leading to better medicines.
In recent years, “deep learning” AI models have often been touted as “working like the brain,” in that they are composed of artificial neurons mimicking those of biological brains. From the perspective of a neuroscientist, however, the differences between deep learning neurons and biological neurons are numerous and distinct. In this blog post we’ll start by describing a few key characteristics of biological neurons, and how they are simplified to obtain deep learning neurons. We’ll then speculate on how these differences impose limits on deep learning networks, and how the movement toward more realistic models of biological neurons might advance AI as we currently know it.
Indeed, a very recent study by OpenAI demonstrates the emergence of complex interactive behaviors among agents trained by reinforcement learning, despite a seemingly impoverished reward system. Notably, rewards were given for team (akin to species) performance, not individual performance—much like all the wolves in a pack are rewarded when a large kill is made.