Daniel Bethell

KAN. Implementation on how to use Kolmogorov-Arnold Networks (KANs) for classification and regression tasks.

MC-CP. All the material needed to use MC-CP and the Adaptive MC Dropout method

cedl. Our Conflict-aware Evidential Deep Learning (C-EDL) method enhances robustness to OOD and adversarial inputs by combining evidence from metamorphic transformations and reducing evidence when conflicts arise, signalling higher uncertainty.

ADVICE. All the material needed to use ADVICE for the safe exploration of reinforcement learning agents.

peer-review-biases. Jupyter Notebook

guide. Python