Manuel Baltieri
manuelbaltieri.bsky.social
Manuel Baltieri
@manuelbaltieri.bsky.social
Chief Researcher at Araya, Tokyo. #ALife, #AI, embodied and enactive #cognition. Information, control and applied category theory for cognitive science.

https://manuelbaltieri.com/
Reposted by Manuel Baltieri
I don't want to delete anything. I simply agree with Barbieri's distinction and claim that for a successful syntactic relationship, there is no need for anticipation or computation.
On that level, the cell is a simple reliable #state machine (transducer) with no place for interpretation of meaning.
March 23, 2025 at 1:53 AM
📌
March 15, 2025 at 12:47 PM
📌
March 8, 2025 at 7:56 AM
Secondly, we discuss how this form of Bayesian filtering is quite simplistic, 1) not making full use of Bayesian updates by ignoring observations from the environment/plant, and 2) assuming that beliefs of equicredible states of the environment are disjoint (they form a partition).

16/16
March 5, 2025 at 2:31 AM
Importantly, this makes use of the fact that we have a Markov category, Rel^+, of possibilistic Markov kernels that can be used to specify beliefs as (sub)sets without assigning them probabilities, but that works very much like other “nice” Markov categories.

15/
March 5, 2025 at 2:31 AM
We then show how this corresponds to a Bayesian filtering interpretation for a reasoner: how a controller modelling its environment can be understood as performing Bayesian filtering on its environment.

14/
March 5, 2025 at 2:31 AM
Firstly, we show that the definition of model between two autonomous system can be “reversed” to build a “possibilistic” version of the internal model principle.

13/
March 5, 2025 at 2:31 AM
After a reasonably self contained overview of string diagrams for Markov categories, and some definitions including Bayesian inference/filtering, their parametrised and conjugate prior versions, we dive into the main result, showing mainly two things.

12/
March 5, 2025 at 2:31 AM
In the second part of the paper, we use results from a recent line of work (link.springer.com/chapter/10.1...) started by some of my collaborators on how to interpret a physical system as performing Bayesian inference, or filtering, using the language of Markov categories.

11/
Interpreting Dynamical Systems as Bayesian Reasoners
A central concept in active inference is that the internal states of a physical system parametrise probability measures over states of the external world. These can be seen as an agent’s beliefs...
link.springer.com
March 5, 2025 at 2:31 AM
Our focus here is mostly technical and has to do almost entirely with control theory, but considering where the conversation started on the other platform, I hope that this will have an impact also in the cognitive and life sciences.

10/
March 5, 2025 at 2:31 AM
This is often taken to be 1) a better formalisation of Conant&Ashby’s good regulator “theorem”, and 2) the reason why talking about “internal models” is necessary in cognitive science, AI/ML/RL, biology and neuroscience.

/9
March 5, 2025 at 2:31 AM