It’s amazing how many empirical features of interactions and collective response can emerge from a simple imperative: to minimize surprise. Out today in PNAS PNASNews - with Conor Heins Richard Mann Karl Friston and colleagues! Centre for the Adv Study of Collective Behaviour Max Planck Society pnas.org/doi/10.1073/pn…

Live now:
Conor Heins Conor Heins ~ Active Inference Insights 019 ~ Collective Behaviour, Attention, Intelligence
youtube.com/watch?v=nf57wi…

With Darius Parvizi-Wayne ~

Our paper was accepted in Entropy. Integrating Husserl's phenomenology with active inference and category theory, we lay out social action and shared goals, setting the stage for S4 of VERSES AI Research intelligence roadmap mdpi.com/1099-4300/26/4… #ActiveInference #SocialCognition

🚨 Preprint 🚨 “Active inference and intentional behaviour,” from VERSES AI Research (Friston, Tommaso Salvatori, Alec Tschantz, p(Alex Kiefer | everything else), Verbelen, MKoudahl, Aswin Paul, Chris L Buckley, me) and collaborators (@TakuyaIsomura, Parr, Adeel Razi, Brett J. Kagan)
arxiv.org/abs/2312.07547 1/8

🚨 Preprint 🚨 Stoked to share “Supervised structure learning,” from VERSES AI Research authors (Friston, Lancelot Da Costa, Alec Tschantz, p(Alex Kiefer | everything else), Tommaso Salvatori, Koudahl, Conor Heins, Verbelen, Chris L Buckley) and collaborators (Neacsu, Sajid, Markovic, Parr)
arxiv.org/abs/2311.10300 1/5

Brilliant conversation with Lancelot Da Costa about active inference, multi agent learning, core knowledge, structure learning and intelligence. youtube.com/watch?v=qxEfcr…

Wow, this looks so cool....combines DL theory with complex systems physics + multi-agent / federated learning !

Thank you for hosting me and the opportunity to present! Was a pleasure visiting Science of Intelligence and meeting many of the amazing ppl there :)

So excited that our latest article on insect goal-direction neurons is published Nature Communications nature.com/articles/s4146…

🚨🧠 We’re hiring at VERSES AI Research 🤖🚨
We’re looking for Machine Learning Researchers to join our Machine Learning Lab, led by Chris L Buckley—as well as Machine Learning Engineers to join our Innovations Lab, led by Mahault Albarracin
Short thread 🧵 1/8

🚨 New target paper accepted in Physics of Life Reviews 🚨 “Path integrals, particular kinds, and strange things,” with Karl Friston, Lancelot Da Costa, Dalton A R Sakthivadivel, Conor Heins, Grigorios A. Pavliotis, Thomas Parr, and yours truly (sciencedirect.com/science/articl…) 1/8

Honored to announce that I'll be writing a book on the FEP and active inference for the The MIT Press @mitpress.bsky.social, tentatively entitled: (Artificial) Intelligence from First Principles: Using the Free Energy Principle and Active Inference for the Study and Design of Ecosystems of Intelligence

Extremely excited to share this survey/manifesto on the past, present, and future of predictive coding (PC), written with a STELLAR team:

arxiv.org/pdf/2308.07870…

Find out what predictive coding *really* is, and the role it could play in the future of machine intelligence.

Today we are open-sourcing SynJax which is a JAX library for efficient probabilistic modeling of structured objects (sequences, segmentations, alignments, trees...). It can compute everything you would expect from a probability distribution: argmax, samples, marginals, entropy...

Excited to announce that our review paper on the free energy principle was just accepted in Physics Reports, the most prestigious journal in all of physics 🪐. This is a momentous achievement for our community🥳. Please share: sciencedirect.com/science/articl…