Restricted Boltzmann Machines (RBMs) and models derived from them have been successfully used as basic building blocks in deep neural networks for automatic features extraction, unsupervised weights initialization, but also as standalone models for density estimation, activity recognition and so on. Thus, their generative and discriminative capabilities, but also their computational time are instrumental to a wide range of applications. The main contribution of his paper is to study the above problems by looking at RBMs and Gaussian RBMs (GRBMs) from a topological perspective, bringing insights from network science, an extension of graph theory which analyzes real world complex networks.
|Number of pages||2|
|Publication status||Published - 11 Nov 2016|
|Event||28th Benelux Conference on Artificial Intelligence, BNAIC 2016 - Hotel Casa, Amsterdam, Netherlands|
Duration: 10 Nov 2016 → 11 Nov 2016
Conference number: 28
|Conference||28th Benelux Conference on Artificial Intelligence, BNAIC 2016|
|Period||10/11/16 → 11/11/16|