Spectral learning of weighted automata

Sp2Learn: A Toolbox for the Spectral Learning of Weighted Automata

Sp2Learn is a Python toolbox for the spectral learning of weighted automata from a set of strings, licensed under Free BSD. This paper gives the main formal ideas behind the spectral learning algorithm and details the content of the toolbox. Use cases and an experimental section are also provided.

Spectral Learning of General Weighted Automata via Constrained Matrix Completion

Many tasks in text and speech processing and computational biology require estimating functions mapping strings to real numbers. A broad class of such functions can be defined by weighted automata. Spectral methods based on the singular value decomposition of a Hankel matrix have been recently proposed for learning a probability distribution represented by a weighted automaton from a training s...

Spectral Learning of Weighted Automata A Forward-Backward Perspective

In recent years we have seen the development of efficient provably correct algorithms for learning Weighted Finite Automata (WFA). Most of these algorithms avoid the known hardness results by defining parameters beyond the number of states that can be used to quantify the complexity of learning automata under a particular distribution. One such class of methods are the so-called spectral algori...

Learning Weighted Automata

Spectral triples of weighted groups

We study spectral triples on (weighted) groups and consider functors between the categories of weighted groups and spectral triples. We study the properties of weights and the corresponding functor for spectral triples coming from discrete weighted groups.