58 citations · 237 across the 23 of their papers we have counts for
29 papers
Variational Filtering for Bayesian Last Layers with an Independent Binary Probit Surrogate
Dimitrije Markovic, Conor Heins, Alexander Tschantz +1
Modern deep classifiers trained by gradient descent need many passes over the data to become accurate, and even then are not always well calibrated; post-hoc temperature scaling co…
Active inference and artificial reasoning
Karl Friston, Lancelot Da Costa, Alexander Tschantz +4
This technical note considers the sampling of outcomes that provide the greatest amount of information about the structure of underlying world models. This generalisation furnishes…
Soft Geometric Inductive Bias for Object Centric Dynamics
Hampus Linander, Conor Heins, Alexander Tschantz +2
Physical systems are naturally parameterized in terms of geometric entities and their transformations. While exact equivariance can be a powerful inductive bias, real-world applica…
AXIOM: Learning to Play Games in Minutes with Expanding Object-Centric Models
Conor Heins, Toon Van de Maele, Alexander Tschantz +11
Current deep reinforcement learning (DRL) approaches achieve state-of-the-art performance in various domains, but struggle with data efficiency compared to human learning, which le…
Bayesian Predictive Coding
Alexander Tschantz, Magnus Koudahl, Hampus Linander +4
Predictive coding (PC) is an influential theory of information processing in the brain, providing a biologically plausible alternative to backpropagation. It is motivated in terms…
Navigation under uncertainty: Trajectory prediction and occlusion reasoning with switching dynamical systems
Ran Wei, Joseph Lee, Shohei Wakayama +10
Predicting future trajectories of nearby objects, especially under occlusion, is a crucial task in autonomous driving and safe robot navigation. Prior works typically neglect to ma…
Variational Bayes Gaussian Splatting
Toon Van de Maele, Ozan Catal, Alexander Tschantz +2
Recently, 3D Gaussian Splatting has emerged as a promising approach for modeling 3D scenes using mixtures of Gaussians. The predominant optimization method for these models relies…
Gradient-free variational learning with conditional mixture networks
Conor Heins, Hao Wu, Dimitrije Markovic +3
Balancing computational efficiency with robust predictive performance is crucial in supervised learning, especially for critical applications. Standard deep learning models, while…
From pixels to planning: scale-free active inference
Karl Friston, Conor Heins, Tim Verbelen +7
This paper describes a discrete state-space model -- and accompanying methods -- for generative modelling. This model generalises partially observed Markov decision processes to in…
Active Inference and Intentional Behaviour
Karl J. Friston, Tommaso Salvatori, Takuya Isomura +10
Recent advances in theoretical biology suggest that basal cognition and sentient behaviour are emergent properties of in vitro cell cultures and neuronal networks, respectively. Su…
Supervised structure learning
Karl J. Friston, Lancelot Da Costa, Alexander Tschantz +10
This paper concerns structure learning or discovery of discrete generative models. It focuses on Bayesian model selection and the assimilation of training data or content, with a s…
Designing Ecosystems of Intelligence from First Principles
Karl J Friston, Maxwell J D Ramstead, Alex B Kiefer +17
This white paper lays out a vision of research and development in the field of artificial intelligence for the next decade (and beyond). Its denouement is a cyber-physical ecosyste…
Capsule Networks as Generative Models
Alex B. Kiefer, Beren Millidge, Alexander Tschantz +1
Capsule networks are a neural network architecture specialized for visual scene recognition. Features and pose information are extracted from a scene and then dynamically routed th…
pymdp: A Python library for active inference in discrete state spaces
Conor Heins, Beren Millidge, Daphne Demekas +4
Active inference is an account of cognition and behavior in complex systems which brings together action, perception, and learning under the theoretical mantle of Bayesian inferenc…
Active Inference in Robotics and Artificial Agents: Survey and Challenges
Pablo Lanillos, Cristian Meo, Corrado Pezzato +8
Active inference is a mathematical framework which originated in computational neuroscience as a theory of how the brain implements action, perception and learning. Recently, it ha…
How particular is the physics of the free energy principle?
Miguel Aguilera, Beren Millidge, Alexander Tschantz +1
The free energy principle (FEP) states that any dynamical system can be interpreted as performing Bayesian inference upon its surrounding environment. In this work, we examine in d…
Understanding the Origin of Information-Seeking Exploration in Probabilistic Objectives for Control
Beren Millidge, Anil Seth, Christopher Buckley
The exploration-exploitation trade-off is central to the description of adaptive behaviour in fields ranging from machine learning, to biology, to economics. While many approaches…
Neural Kalman Filtering
Beren Millidge, Alexander Tschantz, Anil Seth +1
The Kalman filter is a fundamental filtering algorithm that fuses noisy sensory data, a previous state estimate, and a dynamics model to produce a principled estimate of the curren…
Investigating the Scalability and Biological Plausibility of the Activation Relaxation Algorithm
Beren Millidge, Alexander Tschantz, Anil Seth +1
The recently proposed Activation Relaxation (AR) algorithm provides a simple and robust approach for approximating the backpropagation of error algorithm using only local learning…
Relaxing the Constraints on Predictive Coding Models
Beren Millidge, Alexander Tschantz, Anil Seth +1
Predictive coding is an influential theory of cortical function which posits that the principal computation the brain performs, which underlies both perception and learning, is the…
Activation Relaxation: A Local Dynamical Approximation to Backpropagation in the Brain
Beren Millidge, Alexander Tschantz, Anil K Seth +1
The backpropagation of error algorithm (backprop) has been instrumental in the recent success of deep learning. However, a key question remains as to whether backprop can be formul…
Neural and phenotypic representation under the free-energy principle
Maxwell J. D. Ramstead, Casper Hesp, Alec Tschantz +3
The aim of this paper is to leverage the free-energy principle and its corollary process theory, active inference, to develop a generic, generalizable model of the representational…
Control as Hybrid Inference
Alexander Tschantz, Beren Millidge, Anil K. Seth +1
The field of reinforcement learning can be split into model-based and model-free methods. Here, we unify these approaches by casting model-free policy optimisation as amortised var…
Reinforcement Learning as Iterative and Amortised Inference
Beren Millidge, Alexander Tschantz, Anil K Seth +1
There are several ways to categorise reinforcement learning (RL) algorithms, such as either model-based or model-free, policy-based or planning-based, on-policy or off-policy, and…