A Synchronization-Driven Learning Rule for Pattern Separation in Self-Organizing Probabilistic Spiking Neural...

Area of Science:

• Computational Neuroscience
• Artificial Intelligence
• Machine Learning

Background:

• Neuroscience-inspired neural networks offer a path to integrate biological principles with AI.
• Spiking neural networks (SNNs) mimic biological neurons, processing information through temporal spikes.

Purpose of the Study:

• To propose a novel synchronization-based synaptic learning rule for self-organizing probabilistic spiking neural networks (PSNNs).
• To investigate the role of feedback inhibition in network dynamics, stability, and pattern separation.
• To compare the proposed learning rule with conventional Hebbian learning.

Main Methods:

• Developed a synchronization-based synaptic learning rule for PSNNs with feedback inhibition.
• Analyzed network dynamics, stability, and pattern separation under varying inhibition levels.
• Embedded the trained network in a simulated autonomous agent for a navigation task.

Main Results:

• Moderate feedback inhibition optimized network activity, maximizing pattern separation.
• The synchronization-based learning rule demonstrated superior performance over Hebbian learning in achieving stable pattern separation.
• The trained network successfully navigated a simulated environment, identifying and avoiding obstacles.

Conclusions:

• Feedback inhibition and synchronization-driven plasticity are crucial for self-organizing spiking systems.
• Biologically inspired learning mechanisms show potential for computational neuroscience, neuromorphic computing, and cognitive robotics.