Twitter Beğeni Hilesi

Registration for general attendance now open for this year's mathematics of neuroscience conference: neuromonster.org We've got a full schedule of great talks, and would love to have you join us! Also accepting physical/virtual poster submissions until Sept 20th.

Accepted to NeurIPS 🤠🤙

🚨 Preprint 🚨 Stoked to share “Supervised structure learning,” from VERSES AI Research authors (Friston, Lancelot Da Costa, Alec Tschantz, q(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

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

New work accepted at ICLR 2024. It is a much improved version of an Arxiv submission of over a year ago, and describes a simple algorithm to train predictive coding models that is... more stable, efficient, and robust than the standard one :) arxiv.org/pdf/2212.00720…

A new library to train predictive coding networks. A huge comparative study of multiple ways of training them. An advancement over current state-of-the-art. A large discussion on what did not work. All of this, and more, in our new preprint. arxiv.org/pdf/2407.01163

NEW PREPRINT JUST DROPPED 🥳🚨🎉on a new predictive coding algorithm for your (deep) probabilistic models: DIVIDE & CONQUER PREDICTIVE CODING (DCPC), distilled from the hard work of Hao Wu and Tomasso Salvatori! What can it do? Glad you're asking! arxiv.org/abs/2408.05834