Comment by 9q9 | Hacker News Reader

Comment by 9q9 | Hacker News Reader

Parent Full thread

Gambling etc is not the dark-room argument, I've explicitly left out the dark-room.

Coincidentally, Friston's treatment [1] of the dark room is not convincing, but it nicely illustrates Friston's tendency to make ad-hoc adjustments, for example in [1] he talks about "average" surprise, but there are many ways you can average. Which one is it? How for example do the 302 neurons of C elegans average? Saying this is a difficult task is correct given our understanding of neurons in 2020, but the fact that Friston seems to think Free Energy accomodates all possibilities means it in "not even wrong" territory. In it's current shape, Free Energy does not make interesting predictions for neuroscience, and none of the progress in AI/ML has come from the Free Energy millieu either.

If "surprise is used in a very technical statistical sense" means something concrete, precise, for example minimising KL-divergence of states, the question becomes: show me that this is what the brain does. Or build an AI that does something that is competitive with other forms of contemporary AI.

[1] K. Friston et al, Free-Energy Minimization and the Dark-Room Problem https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3347222/

> there are many ways you can average. Which one is it?

I think it is pretty clear from the paper that the average is over time.

The most detailed (and certainly not vague) description is given in "A Free Energy Principle for Biological Systems", Entropy 2012

> How for example do the 302 neurons of C elegans average?

They don't. An agent can optimize an objective without computing it explicitly.

> Free Energy does not make interesting predictions for neuroscience

What is your objection to my proposed prediction above, that we will find brain models with observable activity that follows the FEP?

Friston also has many papers that explain known facts in terms of FEP. I will grant you those are not predictions but they are consistency arguments.

> none of the progress in AI/ML has come from the Free Energy millieu either

Free energy is a dynamical version of variational Bayes, which has had enormous impact in ML/AI.

Regarding average: which average in the sense of: average over what time window? Any specific choice here needs to be justified as happening in the brain.

Regarding "we will find brain models with observable activity that follows the FEP?": abstractly you are saying that your prediction for theory T is that we will eventually confirm T. This does not exclude anything, I can state this for any theory T whatsoever. (For fun, try to instantiate T with outlandish theories, e.g. with "We will eventually find weapons of mass destruction in Irak", or with plausible theories that have failed so far, e.g. "We will eventuallly see supersymmetry". Does your prediction rule anything out?)

Regarding variational Bayes, that was not invented by the Free Energy millieu.

Reply on news.ycombinator.com