arXiv cs.LG
· Papers
Empirical Minimal-Realisation Compression of Deep Neural Networks via Controllability-Observability Tests
arXiv:2607.05457v1 Announce Type: new Abstract: Deep neural networks often contain substantial hidden-state redundancy, but most compression methods operate directly on weights, neurons, or quantised representations without explicitly characterising the dynamical role of internal states. This paper proposes a controlla