Abstract: Systems and methods are disclosed for enhancing artificial neural networks using a computationally modeled ephaptic coupling mechanism to improve adaptability, efficiency, and learning performance. An example system includes a virtual modulation device configured to dynamically adjust one or more ephaptic coupling hyperparameters within an ephaptically coupled artificial neural network (EC-ANN) architecture. The modulation device operates via a Bayesian optimization agent within a closed feedback loop, enabling control over intra-layer field interactions. The virtual modulation device further includes a graphical user interface (GUI) for visualizing training metrics, configuring hyperparameters, and monitoring decision-making by the Bayesian optimization agent, with options for manual override and automated control. The virtual modulation device is integrated with a public key infrastructure and one or more hardware security modules to securely sign, deploy, and manage trained EC-ANN models.