AI RESEARCH
CHLU: The Causal Hamiltonian Learning Unit as a Symplectic Primitive for Deep Learning
arXiv CS.AI
•
ArXi:2603.01768v2 Announce Type: replace-cross Current deep learning primitives dealing with temporal dynamics suffer from a fundamental dichotomy: they are either discrete and unstable (LSTMs) \citep{pascanu_difficulty_2013}, leading to exploding or vanishing gradients; or they are continuous and dissipative (Neural ODEs) \citep{dupont_augmented_2019}, which destroy information over time to ensure stability. We propose the \textbf{Causal Hamiltonian Learning Unit} (pronounced: \textit{clue}), a novel Physics-grounded computational learning primitive.