Echoes of the Past: A Unified Perspective on Fading memory and Echo States
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866913092563107840 |
|---|---|
| author | Ortega, Juan-Pablo Rossmannek, Florian |
| author_facet | Ortega, Juan-Pablo Rossmannek, Florian |
| contents | Recurrent neural networks (RNNs) have become increasingly popular in information processing tasks involving time series and temporal data. A fundamental property of RNNs is their ability to create reliable input/output responses, often linked to how the network handles its memory of the information it processed. Various notions have been proposed to conceptualize the behavior of memory in RNNs, including steady states, echo states, state forgetting, input forgetting, and fading memory. Although these notions are often used interchangeably, their precise relationships remain unclear. This work aims to unify these notions in a common language, derive new implications and equivalences between them, and provide alternative proofs to some existing results. By clarifying the relationships between these concepts, this research contributes to a deeper understanding of RNNs and their temporal information processing capabilities. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_19145 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Echoes of the Past: A Unified Perspective on Fading memory and Echo States Ortega, Juan-Pablo Rossmannek, Florian Machine Learning Dynamical Systems 37N35, 68T05, 93B03 Recurrent neural networks (RNNs) have become increasingly popular in information processing tasks involving time series and temporal data. A fundamental property of RNNs is their ability to create reliable input/output responses, often linked to how the network handles its memory of the information it processed. Various notions have been proposed to conceptualize the behavior of memory in RNNs, including steady states, echo states, state forgetting, input forgetting, and fading memory. Although these notions are often used interchangeably, their precise relationships remain unclear. This work aims to unify these notions in a common language, derive new implications and equivalences between them, and provide alternative proofs to some existing results. By clarifying the relationships between these concepts, this research contributes to a deeper understanding of RNNs and their temporal information processing capabilities. |
| title | Echoes of the Past: A Unified Perspective on Fading memory and Echo States |
| topic | Machine Learning Dynamical Systems 37N35, 68T05, 93B03 |
| url | https://arxiv.org/abs/2508.19145 |