Thursday, 6 July 2017

Retrocausality and AI

Retrocausality is about physical things in the present affecting things in the past. Wow, read it twice. If it sounds to you like breaking the most basic rules of common sense and our most basic intuitions of how things work, you are right, but as weird as it sounds... somehow it makes perfect sense.

Today I found this inspiring article in about retrocausality. Basically it proves that, if the time symmetry found in all known physic laws is to be accepted as a fundamental law, as it actually is, then causality must go on both directions too, so as unreal it could sound to us, macro-sized humans, it is more than plausibly retrocausality is in the very nature of our world.

Once accepted as a possibility, it solves much of the actual issues with quantum theories: action-at-distance, non-locality, Bell theorem... and it is not more or less plausible than other alternatives, like no-time-symmetry, many-worlds or even the Copenhagen model, so by accepting one "counter-intuitive" possibility, quantum world get less intimidating. I buy it!

Reading it reminded me of one the many variations of the Fractal AI I tried in the past, I wrote about it in the post about the Feynman fractal AI, a model where signal travelled back and forth in time. Here you have a naive drawing of it:

The idea was nice and it was as smart as the "standard" fractal AI, but it could not improve it at all, it was just another way of doing the same stuff, but more complicated, so I finally drooped this idea in the bag of the almost-good ones.

Here you have a nice video of it. The different colours are just a trail of visited positions, the real action is on the black spots:

Would it be possible to build neuronal networks that relay on this concept for learning as you use them, NN without a separate learning phase, where signals arrived at different time-shifts could interact? Well, it makes sense to me, as, when a signal gets the incorrect answer, we are actually penalising its past actions by reducing the weight of previously visited neuronal paths.

I am aware LSTM NN basically do that, but I think about a basic model that use it at the most basic levels, and where learning is not based on any gradient but in past actions of wrongly processed signals.

I just find it the natural way to go... but if and only if the universe has a T-symmetry!


  1. The article states retrocausality is the result of the arrow of time that prevents time from being symmetrical.Physical laws are time-symmetrical, but that does not mean time itself is symmetrical. If you run time backwards I believe you have to negate the sign on all charges. (A positron is an electron going backwards in time.) I believe this is part of what's called CPT symmetry (a combination of C, P, and T is symmetrical, not the individual quantities). Feynman pointed out in "Character of Physical Law" that time is not symmetrical because the universe is expanding. The article refers to thermodynamics as why time is not symmetrical, but the 2nd law is not "entropy always decrease". Feynman discussed this in his lectures. This incorrect law is only true for an isolated system and there is no such thing as an isolated system due to black body radiation. It's just an engineering approximation. Feynman gives the precise statement. So I think a more correct 2nd law is "entropy is always emitted". I view the expansion of the universe as going hand-in-hand with the extraction of entropy out of gravitational systems, as those systems emit energy as photons. There is no heat transfer on cosmological scales by theory and experiment, and entropy is always conserved. So each solar system and galaxy must be going a reduction of entropy. Maybe mass contains a normally-ignored entropy. The entropy of the universe is constant on a co-moving volume basis (which is a volume that expands with the Universe). This shows that on a fixed-volume basis (such as solar systems), entropy is decreasing. So the idea that retro-causality is the yin to causality's yang has a lot of support via CPT symmetry and a cosmological view of constant entropy.

  2. correction: "entropy always INCREASES" in that particular sentence