|国家预印本平台
首页|Meta-autoencoders: An approach to discovery and representation of relationships between dynamically evolving classes

Meta-autoencoders: An approach to discovery and representation of relationships between dynamically evolving classes

Meta-autoencoders: An approach to discovery and representation of relationships between dynamically evolving classes

来源:Arxiv_logoArxiv
英文摘要

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.

Assaf Marron、Smadar Szekely、Irun Cohen、David Harel

计算技术、计算机技术

Assaf Marron,Smadar Szekely,Irun Cohen,David Harel.Meta-autoencoders: An approach to discovery and representation of relationships between dynamically evolving classes[EB/OL].(2025-07-12)[2025-07-25].https://arxiv.org/abs/2507.09362.点此复制

评论