4 papers
A Quantifiable Information-Processing Hierarchy Provides a Necessary Condition for Detecting Agency
Brett J. Kagan, Valentina Baccetti, Brian D. Earp +3
As intelligent systems are developed across diverse substrates - from machine learning models and neuromorphic hardware to in vitro neural cultures - understanding what gives a sys…
Brain-MGF: Multimodal Graph Fusion Network for EEG-fMRI Brain Connectivity Analysis Under Psilocybin
Sin-Yee Yap, Fuad Noman, Junn Yong Loo +6
Psychedelics, such as psilocybin, reorganise large-scale brain connectivity, yet how these changes are reflected across electrophysiological (electroencephalogram, EEG) and haemody…
Simulating Biological Intelligence: Active Inference with Experiment-Informed Generative Model
Aswin Paul, Moein Khajehnejad, Forough Habibollahi +2
With recent and rapid advancements in artificial intelligence (AI), understanding the foundation of purposeful behaviour in autonomous agents is crucial for developing safe and eff…
A Principled Bayesian Framework for Training Binary and Spiking Neural Networks
James A. Walker, Moein Khajehnejad, Adeel Razi
We propose a Bayesian framework for training binary and spiking neural networks that achieves state-of-the-art performance without normalisation layers. Unlike commonly used surrog…