Our Paper Accepted in PLOS ONE．In this work, we propose a novel method for controlling neural spikes under noisy conditions using deep unfolding techniques.

In this study, we leveraged Neural SDEs (Neural Stochastic Differential Equations) to achieve precise control of neural spike timing. Our results demonstrate that diverse firing patterns—including regular spiking, bursting, and high-frequency firing—can be accurately controlled even under noisy conditions.

During the writing process, one of the main challenges was bridging mathematical modeling with the learning framework. Nevertheless, we succeeded in shaping this work as a cross-disciplinary study spanning neuroscience, machine learning, and control engineering. The journey to acceptance was a long one, and we are deeply grateful for the guidance and support we received throughout.

F. Sato, M. Ogura, A. Sashie, Y. Bai, M. Shimono, and N. Wakamiya, “Neural SDE-based spike control of noisy neurons,” PLOS One (accepted for publication), 2025.