Active Continual Learning with Metaplastic Binary Bayesian Neural Networks

Always-on edge systems must keep learning as conditions change under tight compute budgets and must detect unreliable predictions. We propose BiMU, a Bayesian update rule for binary neural networks that prevents posterior saturation on long non-stationary streams, sustaining epistemic uncertainty and enabling buffer-free active querying to cut label and backpropagation costs.

We are excited to have presented this work as a poster at ICML 2026 in Seoul, South Korea. The full paper is available on arXiv.