Papers
2
Total Citations
19
H-Index
2
About
John Maher is a researcher at the forefront of bio-inspired robotics and reconfigurable hardware, with a primary focus on evolving adaptive control systems. His work bridges the gap between neural computation and physical hardware, pioneering the use of Spiking Neural Networks (SNNs) implemented on Field Programmable Analogue Arrays (FPAAs). Maher’s key contributions include the development of a reconfigurable hardware evolution platform for SNN-based robotics controllers, as detailed in his 2007 paper (12 citations), and the subsequent advancement of adaptive analogue hardware evolution in his 2008 work (7 citations). In this latter study, he demonstrated how fixed-architecture, feed-forward SNNs could be trained using a Genetic Algorithm (GA) to control an obstacle-avoidance simulated robot, showcasing the potential for real-time, adaptive behaviour in autonomous systems. Though his citation counts are modest, Maher’s work is notable for its innovative integration of hardware evolution with neural control, laying groundwork for low-power, analogue computing in robotics. His research remains a valuable reference for those exploring the intersection of evolutionary computation, reconfigurable electronics, and neuromorphic engineering.
Research Focus
Key Achievements
Top Papers
- 1
- 2