Synaptic bundle theory for spike-driven sensor-motor system: More than eight independent synaptic bundles collapse reward-STDP learning
This work addresses the challenge of building stable learning systems with spikes for artificial sensor-motor control, which is incremental as it identifies specific parameter ranges to enable further study of spike functions.
The study tackled the problem of learning collapse in spike-driven sensor-motor systems when using too many motor neurons or independent synaptic bundles, finding that learning fails beyond a critical limit but succeeds faster with fewer motor neurons. It identified that weight updates moving opposite to the optimal direction explain these results.
Neuronal spikes directly drive muscles and endow animals with agile movements, but applying the spike-based control signals to actuators in artificial sensor-motor systems inevitably causes a collapse of learning. We developed a system that can vary \emph{the number of independent synaptic bundles} in sensor-to-motor connections. This paper demonstrates the following four findings: (i) Learning collapses once the number of motor neurons or the number of independent synaptic bundles exceeds a critical limit. (ii) The probability of learning failure is increased by a smaller number of motor neurons, while (iii) if learning succeeds, a smaller number of motor neurons leads to faster learning. (iv) The number of weight updates that move in the opposite direction of the optimal weight can quantitatively explain these results. The functions of spikes remain largely unknown. Identifying the parameter range in which learning systems using spikes can be constructed will make it possible to study the functions of spikes that were previously inaccessible due to the difficulty of learning.