BioOSS: A Bio-Inspired Oscillatory State System with Spatio-Temporal Dynamics
This work addresses the need for more biologically plausible neural models in AI, particularly for applications involving spatio-temporal data, though it appears incremental in building on existing oscillatory systems.
The paper tackled the problem of deep learning architectures not capturing biological neural oscillatory dynamics by proposing BioOSS, a bio-inspired oscillatory state system that emulates wave-like propagation, and demonstrated superior performance and interpretability on synthetic and real-world tasks.
Today's deep learning architectures are primarily based on perceptron models, which do not capture the oscillatory dynamics characteristic of biological neurons. Although oscillatory systems have recently gained attention for their closer resemblance to neural behavior, they still fall short of modeling the intricate spatio-temporal interactions observed in natural neural circuits. In this paper, we propose a bio-inspired oscillatory state system (BioOSS) designed to emulate the wave-like propagation dynamics critical to neural processing, particularly in the prefrontal cortex (PFC), where complex activity patterns emerge. BioOSS comprises two interacting populations of neurons: p neurons, which represent simplified membrane-potential-like units inspired by pyramidal cells in cortical columns, and o neurons, which govern propagation velocities and modulate the lateral spread of activity. Through local interactions, these neurons produce wave-like propagation patterns. The model incorporates trainable parameters for damping and propagation speed, enabling flexible adaptation to task-specific spatio-temporal structures. We evaluate BioOSS on both synthetic and real-world tasks, demonstrating superior performance and enhanced interpretability compared to alternative architectures.