Thomas Miconi

Papers

Total Citations

H-Index

About

Thomas Miconi is a leading researcher at the intersection of artificial intelligence and computational neuroscience, best known for his pioneering work on biologically plausible learning algorithms. His most cited paper, "Brain-inspired learning in artificial neural networks: a review" (2023, 5 citations), critically examines the fundamental differences between artificial neural networks and biological brains, proposing novel pathways for more efficient, adaptive learning systems. Miconi’s major contributions include the development of Hebbian-like learning rules and synaptic plasticity mechanisms that bridge the gap between deep learning and natural intelligence. His research has been instrumental in advancing few-shot learning, meta-learning, and continual learning—areas where traditional backpropagation falls short. With a growing citation impact, Miconi’s work has influenced both AI practitioners and neuroscientists seeking to understand how brains learn from limited data. Notably, his algorithms have been applied to robotics and reinforcement learning, demonstrating that brain-inspired principles can lead to more robust and sample-efficient AI. For students and researchers, Miconi’s work offers a compelling vision: building machines that learn not just faster, but more like living beings.