6 papers
A Bio-Inspired Minimal Model for Non-Stationary K-Armed Bandits
Krubeal Danieli, Mikkel Elle Lepperød
While reinforcement learning algorithms have made significant progress in solving multi-armed bandit problems, they often lack biological plausibility in architecture and dynamics.…
Reservoir Computing with Evolved Critical Neural Cellular Automata
Sidney Pontes-Filho, Stefano Nichele, Mikkel Lepperød
Criticality is a behavioral state in dynamical systems that is known to present the highest computation capabilities, i.e., information transmission, storage, and modification. The…
The Generalist Brain Module: Module Repetition in Neural Networks in Light of the Minicolumn Hypothesis
Mia-Katrin Kvalsund, Mikkel Elle Lepperød
While modern AI continues to advance, the biological brain remains the pinnacle of neural networks in its robustness, adaptability, and efficiency. This review explores an AI archi…
ARC-NCA: Towards Developmental Solutions to the Abstraction and Reasoning Corpus
Etienne Guichard, Felix Reimers, Mia Kvalsund +2
The Abstraction and Reasoning Corpus (ARC), later renamed ARC-AGI, poses a fundamental challenge in artificial general intelligence (AGI), requiring solutions that exhibit robust a…
EngramNCA: a Neural Cellular Automaton Model of Memory Transfer
Etienne Guichard, Felix Reimers, Mia Kvalsund +2
This study introduces EngramNCA, a neural cellular automaton (NCA) that integrates both publicly visible states and private, cell-internal memory channels, drawing inspiration from…
Exploring Biologically Inspired Mechanisms of Adversarial Robustness
Konstantin Holzhausen, Mia Merlid, HÃ¥kon Olav Torvik +2
Backpropagation-optimized artificial neural networks, while precise, lack robustness, leading to unforeseen behaviors that affect their safety. Biological neural systems do solve s…