J. David Schaffer

Papers

Total Citations

H-Index

About

J. David Schaffer is a pioneering researcher at the intersection of evolutionary computation, neural networks, and robotics, whose work has significantly advanced our understanding of biologically inspired machine intelligence. He is best known for applying evolutionary algorithms to the design and optimization of spiking neural networks (SNNs) — computational models that closely mimic the behavior of biological neurons — particularly for robotic control applications. His landmark 2011 paper, "Evolving Spiking Neural Networks for Robot Control," which has garnered 42 citations, demonstrated that robot "brains" could be evolved through imitation learning to perform complex sensory-motor tasks such as light-seeking and obstacle avoidance, blending evolutionary methods with behavioral mimicry in an elegant and practical framework. Schaffer's more recent work continues to push these boundaries, exploring how evolutionary computation can address the persistent challenge of designing SNN topologies for tasks of varying complexity — encapsulated in his compelling thesis that "the topology IS the algorithm." His contributions offer students and researchers a rich foundation for understanding how nature-inspired computation can unlock new capabilities in autonomous robotics and neuromorphic computing.