Sam McKennoch
Papers
1
Total Citations
2
H-Index
1
About
Sam McKennoch is a researcher whose work lies at the intersection of computational neuroscience and robotics, with a particular focus on biologically plausible neural networks for embedded systems. His most cited paper, "Theta Neuron Networks: Robustness to Noise in Embedded Applications" (2007, 2 citations), explores the use of Theta Neuron Networks (TNNs) for robotic control, specifically training a one-layer TNN to execute a Braitenberg obstacle avoidance algorithm on a Khepera robot. This work is notable for its emphasis on the Theta neuron model, which offers greater biological realism compared to the leaky integrate-and-fire model commonly used in Spiking Neural Networks. McKennoch's research demonstrates the potential of these networks for robust performance in noisy, real-world environments, a critical consideration for embedded applications. While his citation count is modest, his contributions highlight a forward-thinking approach to bridging neural computation and robotics, offering insights into how more biologically accurate models can enhance the reliability and efficiency of autonomous systems.
Research Focus
Key Achievements
Top Papers
- 1Theta Neuron Networks: Robustness to Noise in Embedded Applications2 citations · 2007