Biomimetic Visual Information Spatiotemporal Encoding Method for In Vitro Biological Neural Networks

摘要

The integration of in vitro biological neural networks (BNNs) with robotic systems to explore their information processing and adaptive learning in practical tasks has gained significant attention in the fields of neuroscience and robotics. However, existing BNN-based robotic systems cannot perceive the visual environment due to the inefficiency of sensory information encoding methods. In this study, we propose a biomimetic visual information spatiotemporal encoding method based on improved delayed phase encoding. This method transforms high-dimensional images into a series of pulse sequences through convolution, temporal delay, alignment, and compression for BNN stimuli. We conduct three stages of unsupervised training on in vitro BNNs using high-density microelectrode arrays (HD-MEAs) to validate the potential of the proposed encoding method for image recognition tasks. The neural activity is decoded via a logistic regression model. The experimental results show that the firing patterns of BNNs with different spatiotemporal stimuli are highly separable in the feature space. After the third training stage, the image recognition accuracy reaches 80.33% ± 7.94%, which is 13.64% higher than that of the first training stage. Meanwhile, the BNNs exhibit significant increases in the connection number, connection strength, and inter-module participation coefficient after unsupervised training. These results demonstrate that the proposed method significantly enhances the functional connectivity and cross-module information exchange in BNNs.