Meta-autoencoders: An approach to discovery and representation of relationships between dynamically evolving classes
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866915386084032512 |
|---|---|
| author | Marron, Assaf Szekely, Smadar Cohen, Irun Harel, David |
| author_facet | Marron, Assaf Szekely, Smadar Cohen, Irun Harel, David |
| contents | An autoencoder (AE) is a neural network that, using self-supervised training, learns a succinct parameterized representation, and a corresponding encoding and decoding process, for all instances in a given class. Here, we introduce the concept of a meta-autoencoder (MAE): an AE for a collection of autoencoders. Given a family of classes that differ from each other by the values of some parameters, and a trained AE for each class, an MAE for the family is a neural net that has learned a compact representation and associated encoder and decoder for the class-specific AEs. One application of this general concept is in research and modeling of natural evolution -- capturing the defining and the distinguishing properties across multiple species that are dynamically evolving from each other and from common ancestors. In this interim report we provide a constructive definition of MAEs, initial examples, and the motivating research directions in machine learning and biology. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_09362 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Meta-autoencoders: An approach to discovery and representation of relationships between dynamically evolving classes Marron, Assaf Szekely, Smadar Cohen, Irun Harel, David Machine Learning Populations and Evolution An autoencoder (AE) is a neural network that, using self-supervised training, learns a succinct parameterized representation, and a corresponding encoding and decoding process, for all instances in a given class. Here, we introduce the concept of a meta-autoencoder (MAE): an AE for a collection of autoencoders. Given a family of classes that differ from each other by the values of some parameters, and a trained AE for each class, an MAE for the family is a neural net that has learned a compact representation and associated encoder and decoder for the class-specific AEs. One application of this general concept is in research and modeling of natural evolution -- capturing the defining and the distinguishing properties across multiple species that are dynamically evolving from each other and from common ancestors. In this interim report we provide a constructive definition of MAEs, initial examples, and the motivating research directions in machine learning and biology. |
| title | Meta-autoencoders: An approach to discovery and representation of relationships between dynamically evolving classes |
| topic | Machine Learning Populations and Evolution |
| url | https://arxiv.org/abs/2507.09362 |