2025/01/01 by Giovanni di Sarra, Barbara Bravi, Yasser Roudi · 1 voice · 1 citation
Biochemistry, Genetics and Molecular Biology · Computer Science · Engineering · Materials Science · Physics and Astronomy · #Advanced Memory and Neural Computing #Extracellular vesicles in disease #Machine Learning in Materials Science #cond-mat.dis-nn #cs.LG #physics.data-an
paper · pdf · doi:10.1209/0295-5075/ada636
openalex publication_date 2025/01/01 · arxiv published 2025/01/08 · arxiv updated 2025/01/08 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Abstract Restricted Boltzmann machines are simple yet powerful neural networks. They can be used for learning structure in data, and are used as a building block of more complex neural architectures. At the same time, their simplicity makes them easy to use, amenable to theoretical analysis, yielding interpretable models in applications. Here, we focus on reviewing the role that the activation functions, describing the input-output relationship of single neurons in RBM, play in the functionality of these models. We discuss recent theoretical results on the benefits and limitations of different activation functions. We also review applications to biological data analysis, namely neural data analysis, where RBM units are mostly taken to have sigmoid activation functions and binary units, to protein data analysis and immunology where non-binary units and non-sigmoid activation functions have recently been shown to yield important insights into the data. Finally, we discuss open problems addressing which can shed light on broader issues in neural network research.