Now showing 1 - 3 of 3
No Thumbnail Available
Publication

tanh Neurons are Bayesian Decision Makers

2021 , Bauckhage, Christian , Sifa, Rafet , Hecker, Dirk

The hyperbolic tangent (tanh) is a traditional choice for the activation function of the neurons of an artificial neural network. Here, we go through a simple calculation that shows that this modeling choice is linked to Bayesian decision theory. Our brief, tutorial-like discussion is intended as a reference to an observation rarely mentioned in standard textbooks.

No Thumbnail Available
Publication

Max-Sum Dispersion via Quantum Annealing

2019 , Bauckhage, Christian , Sifa, Rafet , Hecker, Dirk , Wrobel, Stefan

We devise an Ising model for the max-sum dispersion problem which occurs in contexts such as Web search or text summarization. Given this Ising model, max-sum dispersion can be solved on adiabatic quantum computers; in proof of concept simulations, we solve the corresponding Schrödinger equations and observe our approach to work well.

No Thumbnail Available
Publication

A QUBO Formulation of the k-Medoids Problem

2019 , Bauckhage, Christian , Piatkowski, Nico , Sifa, Rafet , Hecker, Dirk , Wrobel, Stefan

We are concerned with k-medoids clustering and propose aquadratic unconstrained binary optimization (QUBO) formulation of the problem of identifying k medoids among n data points without having to cluster the data. Given our QUBO formulation of this NP-hard problem, it should be possible to solve it on adiabatic quantum computers.