Reservoir computers (RCs) are a class of recurrent neural networks that incorporate brain-inspired principles and provide an efficient alternative to deep learning. With fixed random internal connections and trained output weights, they simplify lear...
The success of deep learning methods over the past decade has been partially shrouded in the shadow of adversarial attacks. Even a tiny undetectable deformation can lead to vicious misleading targeted at safety-critical applications. In contrast, the...
Proceedings of the National Academy of Sciences of the United States of America
Nov 18, 2025
The architectures of biological neural networks result from developmental processes shaped by genetically encoded rules, biophysical constraints, stochasticity, and learning. Understanding these processes is crucial for comprehending neural circuits'...
Neural Cellular Automata have proven to be effective in various fields, with numerous biologically inspired applications. Particularly, neural cellular automata have been proven to be successful models for procedural generation of textures. They mode...
Proceedings of the National Academy of Sciences of the United States of America
Nov 13, 2025
Covert visual attention allows the brain to select different regions of the visual world without eye movements. Predictive cues of a target location orient covert attention and improve perceptual performance. In most computational models, researchers...
Spiking Neural Networks (SNNs), designed to more accurately model the brain's neurobiological processes, have been proposed as energy-efficient alternatives to conventional Artificial Neural Networks (ANNs), which typically incur high computational a...
Proceedings of the National Academy of Sciences of the United States of America
Oct 31, 2025
Memory consolidation refers to a process of engram reorganization and stabilization that is thought to occur primarily during sleep through a combination of neural replay, homeostatic plasticity, synaptic maturation, and pruning. From a computational...
The brain network damage provoked by a neurological disease can be modelled as the result of the action of an operator, K, acting on the brain, inspired by physics. Here, we explore the matrix formulation of K, analysing eigenvalues and eigenvectors,...
Neural coupling in both neuroscience and AI emerges dynamic oscillatory patterns that encode abstract concepts. To that end, we hypothesize that a deeper understanding of the neural mechanisms that determine brain rhythms could inspire next-generatio...
The time-elapsed model for neural assemblies is a nonlinear age-structured equation where the renewal term describes the network activity and influences the discharge rate, possibly with a delay due to the length of connections. We first solve a long...
Join thousands of healthcare professionals staying informed about the latest AI breakthroughs in medicine. Get curated insights delivered to your inbox.