Abstract Despite the incremental nature of Dynamic Syntax (DS), semantic grounding it remains that predicate logic, itself grounded in set theory, so is poorly suited to expressing rampantly context-relative word meaning, and related phenomena such as judgements similarity needed for modelling disambiguation. Here, we show how DS can be assigned a compositional distributional semantics which en...

The ability to find short representations, i.e. compress data, is crucial for many intelligent systems. We present a theory of incremental compression showing that arbitrary data strings, can be described by set features, compressed searching those features incrementally, which results in partition the information content string into complete pairwise independent pieces. description length this...

Complete verification of deep neural networks (DNNs) can exactly determine whether the DNN satisfies a desired trustworthy property (e.g., robustness, fairness) on an infinite set inputs or not. Despite tremendous progress to improve scalability complete verifiers over years individual DNNs, they are inherently inefficient when deployed is updated its inference speed accuracy. The inefficiency ...