no code implementations • 14 May 2022 • Giuseppe Genovese
We identify an effective energy function describing the zero-temperature landscape on the visible units and depending only on the tail behaviour of the hidden layer prior distribution.
1 code implementation • 22 Feb 2022 • Giuseppe Genovese, Ashkan Nikeghbali, Nicola Serra, Gabriele Visentin
We introduce a new portfolio credit risk model based on Restricted Boltzmann Machines (RBMs), which are stochastic neural networks capable of universal approximation of loss distributions.
no code implementations • 15 May 2020 • Giuseppe Genovese
We study the free energy of a most used deep architecture for restricted Boltzmann machines, where the layers are disposed in series.
no code implementations • 20 Feb 2017 • Adriano Barra, Giuseppe Genovese, Peter Sollich, Daniele Tantari
Restricted Boltzmann Machines are described by the Gibbs measure of a bipartite spin glass, which in turn corresponds to the one of a generalised Hopfield network.
no code implementations • 9 Dec 2016 • Adriano Barra, Giuseppe Genovese, Peter Sollich, Daniele Tantari
We study Generalised Restricted Boltzmann Machines with generic priors for units and weights, interpolating between Boolean and Gaussian variables.