Vera Koponen

activity

20242026

collaborators

7 papers

cs.AI2026

A concentration result for multilayer feedforward neural networks

Vera Koponen

We consider for an arbitrary fixed $ρ$ and for each positive integer $n$ a multilayer feedforward artificial neural network with $ρ$ layers, $n$ neurons in the first layer (the inp…

math.CO2026

Exponential random graph models with soft clique constraints

Yasmin Tousinejad, Vera Koponen

Let $r \geq 3$ be fixed, and let $G_{n}$ be the set of all simple graphs with vertex set $[n] = {1, \dots, n}$ . We consider an exponential random graph model which gives higher…

math.LO2026

Random coloured digraphs defined by a Markov logic network

Yasmin Tousinejad, Vera Koponen

A Markov Logic Network (MLN) is a probabilistic relational model used in Statistical Relational Artificial Intelligence for defining a probability distribution on the set of possib…

math.LO2025

Notions of rank and independence in countably categorical theories

Vera Koponen

For an $ω$ -categorical theory $T$ and model $M$ of $T$ we define a hierarchy of ranks, the $n$ -ranks for $n < ω$ which only care about imaginary elements ``up to level $n…

cs.AI2025

Domain size asymptotics for Markov logic networks

Vera Koponen

A Markov logic network (MLN) $M$ determines a probability distribution $P_{n}^{M}$ on the set $W_{n}$ of structures, or ``possible worlds'', with doma…

cs.LO2025

A convergence law for continuous logic and continuous structures with finite domains

Vera Koponen

We consider continuous relational structures with finite domain $[n] := {1, \dots, n}$ and a many valued logic, $C L A$ , with values in the unit interval and which uses continuous…