Unified Complex-valued Neural Network: A Magnitude-Phase Computational Model for Event-Driven Neuromorphic Learning
For neuromorphic and edge-AI applications, this work proposes a new neural computational model that unifies value encoding and timing dynamics, though the evaluation is limited to two tasks and lacks comparison with state-of-the-art methods.
The paper introduces a Unified Complex-valued Neuron (UCN) model that integrates continuous activation and phase-driven event generation for spatiotemporal learning. Evaluated on object tracking and Lorenz attractor learning, the UCN-based network achieves accurate, stable, and interpretable performance with sparse event-driven computation.
Artificial neural networks (ANN) provide accurate continuous-valued representation, whereas spiking neural networks (SNN) offer event-driven temporal processing, yet both paradigms face limitations when value encoding and timing dynamics must be learned within a single computational structure. This paper introduces a network based on Unified Complex-valued Neuron (UCN), a new neural computational model that integrates continuous activation and phase-driven event generation through an asymmetric complex-valued state. In the UCN, magnitude encodes signal strength while phase governs intrinsic temporal evolution and valued spike emission. A foundational training framework combining backpropagation (BP) and backpropagation through time (BPTT) is first developed to optimize magnitude and phase pathways in a unified way. To reduce computational complexity, an event-driven adaptive phase learning (EAPL) rule is then introduced as a more efficient alternative. The proposed model is evaluated through object tracking and Lorenz attractor learning. Results demonstrate that UCN-based Network (UCNN) provides accurate, stable, and interpretable spatiotemporal learning while preserving sparse event-driven computation for neuromorphic and edge-AI applications.