Derivatives of Turing machines in Linear Logic
arXiv:1805.11813
Abstract
We calculate denotations under the Sweedler semantics of the Ehrhard-Regnier derivatives of various encodings of Turing machines into linear logic. We show that these derivatives calculate the rate of change of probabilities naturally arising in the Sweedler semantics of linear logic proofs. The resulting theory is applied to the problem of synthesising Turing machines by gradient descent.
arXiv comment62 pages, moved the section on naive Bayesian observers earlier (Section 6.2) with slight changes to notation, references added in the introduction to Section 7 and related work in Remark 7.16
References in corpus (4)
- TerpreT: A Probabilistic Programming Language for Program Induction
- On manifolds with corners
- On Learning to Think: Algorithmic Information Theory for Novel Combinations of Reinforcement Learning Controllers and Recurrent Neural World Models
- Towards common-sense reasoning via conditional simulation: legacies of Turing in Artificial Intelligence