Issue |
EPL
Volume 149, Number 2, January 2025
|
|
---|---|---|
Article Number | 21002 | |
Number of page(s) | 7 | |
Section | Statistical physics and networks | |
DOI | https://doi.org/10.1209/0295-5075/ada636 | |
Published online | 23 January 2025 |
The unbearable lightness of restricted Boltzmann machines: Theoretical insights and biological applications
1 Kavli Institute for Systems Neuroscience, NTNU - Olav Kyrres Gate 30, Trondheim, Norway
2 Department of Mathematics, Imperial College London - London, SW7 2AZ, UK
3 Department of Mathematics, King's College London-Strand - London, WC2R 2LS, UK
Received: 30 July 2024
Accepted: 6 January 2025
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.
© 2025 The author(s)
Published by the EPLA under the terms of the Creative Commons Attribution 4.0 International License (CC-BY). Further distribution of this work must maintain attribution to the author(s) and the published article's title, journal citation, and DOI.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.