Evaluating Encoding Strategies for Closed-Loop Classification in Biological Neural Networks

2026-07-15

AI Summary

This study investigates how optimizing spatiotemporal stimulus encoding can enhance the processing efficiency and adaptability of biological neural networks in closed-loop classification tasks. Using multi-electrode arrays (MEAs), the authors applied various temporal coding strategies—including rate, phase, time-to-first-spike, and burst-based encoding—to in vitro cultured neural networks, combined with spatial electrode selection for closed-loop stimulation and performance evaluation. The results demonstrate that burst-based temporal encoding achieves a classification accuracy of 95.6% in a binary task, significantly outperforming other encoding schemes, and reveal a high sensitivity of classification performance to the spatial distribution of stimulating electrodes. This work establishes temporal encoding as a critical design dimension in bio-digital hybrid computing and underscores the necessity of jointly optimizing both spatial and temporal aspects of neural stimulation.

Abstract

Interfacing with Biological Neural Networks (BNNs) requires encoding information into stimulation patterns that can be effectively processed and that enable the underlying system to adapt. Nevertheless, the role of stimulation encoding remains poorly understood. In this work, we compare multiple encoding strategies, including rate-based, phase-based, burst-based, and time-to-first-spike temporal encodings, in a closed-loop neural classification task using cultured BNNs. We encode visual inputs as spatiotemporal stimulation patterns delivered via a Multi-Electrode Array (MEA) and evaluate classification performance for each encoding scheme. We find that burst-based temporal encoding yields the highest observed performance, achieving up to 95.6 % accuracy in a binary classification task, compared to substantially lower performance from rate- and phase-based approaches. We further show that performance is highly sensitive to the spatial distribution of stimulation, with suboptimal electrode selection significantly degrading accuracy. These findings indicate that effective interfacing with biological neural systems requires the joint optimization of temporal and spatial encoding strategies, and highlight temporal encoding as a key design dimension for bio-digital computing.

Problem

• Encoding Strategies
• Closed-Loop Classification
• Biological Neural Networks
• Temporal Encoding
• Neural Interfacing

Innovation

• burst-based encoding
• temporal encoding
• closed-loop classification
• biological neural networks
• spatiotemporal stimulation