[karmickoala]

Someone highlighted this on ML Twitter:

> “The enormous amount of time, effort & money that goes into such projects might be overkill. I don’t need to know the precise details of the wiring of each cell and each synapse in the brain. What I need to know, instead, is the organizational principles that wire them together.”

I think this endeavor might still be useful, e.g., it may help identify missing elements in a model. An example of that in another field: astrophysicists did know the organizational principles to build galaxy kinematics models, but only using the Schwarzchild's method---which is akin to mapping the galaxy---they were able to confirm that supermassive black holes should be at the center of most galaxies. Hence, both approaches (machine learning and mapping the brain) may walk hand in hand, helping identify such organizational principles.

[melling]

There’s always someone with an opposing opinion.

In the 1990’s there was a debate on the value of the Supercollider vs the Hubble. People would argue that the Hubble was of little scientific value.