George Ellis
Papers
2
Total Citations
4
H-Index
2
About
George Ellis is a researcher at the intersection of neuroscience and artificial intelligence, with a primary focus on developing biologically-inspired neural network architectures. His major contributions center on the creation of the Salience-Affected Artificial Neural Network (SANN), a novel model that simulates how neuromodulators like dopamine and noradrenaline are diffusely distributed through neocortical regions to influence neural dynamics. This innovative framework enables one-time learning—a capability that mirrors the brain’s ability to form lasting memories from a single, salient experience. Ellis’s work bridges the gap between computational models and biological cognition, offering a pathway toward more efficient, human-like learning in AI systems. While his most-cited papers have garnered 2 citations each, their conceptual novelty positions them as foundational contributions to the emerging field of neuromodulatory AI. By integrating principles of salience and neurotransmitter function, Ellis is advancing our understanding of how machines might replicate the brain’s remarkable adaptability, making his research a compelling read for students and researchers exploring the future of intelligent systems.
Research Focus
Key Achievements
Top Papers
- 1
- 2Biologically-inspired Salience Affected Artificial Neural Network (SANN)2 citations · 2019