Larry Bull

About

Larry Bull is a pioneering researcher whose work sits at the intersection of evolutionary computation, neuromorphic computing, and autonomous robotics. Best known for his groundbreaking contributions to learning classifier systems and neuroevolutionary approaches, Bull has spent decades pushing the boundaries of how artificial systems learn and adapt. His most influential work, "Evolution of Plastic Learning in Spiking Networks via Memristive Connections" (2012, 73 citations), introduced memristors as plastic synaptic connections within spiking neural networks — a landmark contribution to neuromorphic computing that inspired subsequent studies on resistive memory-based learning. His sustained interest in biologically plausible hardware is further evidenced by a series of related papers exploring unipolar memristor spiking networks and variable resistive memories. Equally significant is his work on learning classifier systems applied to real-world robotics, including self-adaptive mutation strategies and autonomous mobile robot control, demonstrating that theoretical models can translate into tangible physical systems. His research on imitation-enhanced reinforcement learning in multi-agent environments reflects a broader commitment to understanding emergent, socially-informed intelligence. Collectively accumulating hundreds of citations, Bull's body of work represents an essential reference for researchers exploring adaptive computation, brain-inspired hardware, and intelligent autonomous systems.

Research Focus

Key Achievements

Top Papers

1. 1
   Evolution of Plastic Learning in Spiking Networks via Memristive Connections

   73 citations · 2012
2. 2
   A Neural Learning Classifier System with Self-Adaptive Constructivism for Mobile Robot Control

   47 citations · 2006
3. 3
   TCS Learning Classifier System Controller on a Real Robot

   32 citations · 2002
4. 4
   Evolving Spiking Networks with Variable Resistive Memories

   25 citations · 2013
5. 5
   X-TCS: Accuracy-based Learning Classifier System Robotics

   23 citations · 2005
6. 6
   Towards evolving spiking networks with memristive synapses

   17 citations · 2011
7. 7
   Embodied imitation-enhanced reinforcement learning in multi-agent systems

   16 citations · 2013
8. 8
   Self-adaptation in classifier system controllers

   14 citations · 2001
9. 9
   Evolving unipolar memristor spiking neural networks

   11 citations · 2015
10. 10
    Self-Adaptive Mutation in ZCS Controllers

    11 citations · 2000

Key Collaborators

Contact & Links