Hybrid predictive coding: Inferring, fast and slow
The study proposes a hybrid predictive coding model that integrates both amortized and iterative inference to enhance perceptual beliefs through neura…
Category: Resources
Active Inference in String Diagrams: A Categorical Account of Predictive Processing and Free Energy
The article presents a categorical approach to Predictive Processing and Active Inference using string diagrams within a monoidal category. It include…
Collective behavior from surprise minimization
The study explores collective motion in animals, proposing a model based on active inference, where behavior aims to minimize surprise. This approach …
Revolutionary Proposal Emerges for Effective AI Governance
HSML, a programming language for the Spatial Web, facilitates effective AI governance by creating computable context. This advancement enhances AI's p…
Steps towards a minimal unifying model of consciousness: An integration of models of consciousness based on the free energy principle
The paper evaluates the "inner screen model" of consciousness, derived from the free energy principle (FEP), as a potential minimal unifying model (MU…
Focus: Object-centric world models for robotics manipulation
The research paper introduces FOCUS, a model-based agent that learns an object-centric world model for robotics manipulation. It addresses the challen…
Mastering the unsupervised reinforcement learning benchmark from pixels
The paper discusses advancements in unsupervised reinforcement learning (RL) from visual inputs. The authors propose a method using unsupervised model…
Forward-Looking MIMO-SAR for Enhanced Radar Imaging in Autonomous Mobile Robots
The paper examines forward-looking multiple-input multiple-output synthetic aperture radar (FL-MIMO-SAR) for enhancing imaging in autonomous mobile ro…
On efficient computation in active inference
The paper addresses challenges in employing active inference for intelligent behavior due to high computational costs and target distribution specific…
Causal Inference via Predictive Coding
The paper presents a novel approach to causal inference using predictive coding, a method inspired by neuroscience. By modifying the inference process…