Extensional Properties of Recurrent Neural Networks
A property of a recurrent neural network (RNN) is called \emph{extensional} if, loosely speaking, it is a property of the function computed by the RNN rather than a property of the RNN algorithm. Many properties of interest in RNNs are extensional, for example, robustness against small changes of input or good clustering of inputs. Given an RNN, it is natural to ask whether it has such a property. We give a negative answer to the general question about testing extensional properties of RNNs. Namely, we prove a version of Rice's theorem for RNNs: any nontrivial extensional property of RNNs is undecidable.
Code (0)
등록된 구현이 없습니다.
Tasks
ClusteringSimilar Papers 제목 키워드 기반
The role of extensional rheology in the oral phase of swallowing: an in vitro study
Swallowing disorders deteriorate significantly the quality of life and can be lifethreatening. Texture modification using shear thinning food thickeners have proven effective in the management of dysphagia. Some studies …
ManagementEmbedding Ontologies via Incorporating Extensional and Intensional Knowledge
Ontologies contain rich knowledge within domain, which can be divided into two categories, namely extensional knowledge and intensional knowledge. Extensional knowledge provides information about the concrete instances t…
Language ModelingLanguage ModellingLink PredictionOntology Embedding+1Minimum Model Semantics for Extensional Higher-order Logic Programming with Negation
Extensional higher-order logic programming has been introduced as a generalization of classical logic programming. An important characteristic of this paradigm is that it preserves all the well-known properties of tradit…
NegationIntensional Inheritance Between Concepts: An Information-Theoretic Interpretation
This paper addresses the problem of formalizing and quantifying the concept of "intensional inheritance" between two concepts. We begin by conceiving the intensional inheritance of $W$ from $F$ as the amount of informati…
Lifting Structural Tractability to CSP with Global Constraints
A wide range of problems can be modelled as constraint satisfaction problems (CSPs), that is, a set of constraints that must be satisfied simultaneously. Constraints can either be represented extensionally, by explicitly…