Exploring Flip Flop memories and beyond: training Recurrent Neural Networks with key insights | ||
| dc.conicet.organizacion | Consejo Nacional de Investigaciones Científicas y Técnicas | |
| dc.conicet.organizacion | Universidad Nacional de Quilmes. Departamento de Ciencia y Tecnología | |
| dc.conicet.organizacion | University Aarhus | |
| dc.contributor.author | Jarne, Cecilia Gisele | |
| dc.date.issued | 2024-03 | |
| dc.description.abstract | Training neural networks to perform different tasks is relevant across various disciplines. In particular, Recurrent Neural Networks (RNNs) are of great interest in Computational Neuroscience. Open-source frameworks dedicated to Machine Learning, such as Tensorflow and Keras have produced significant changes in the development of technologies that we currently use. This work contributes by comprehensively investigating and describing the application of RNNs for temporal processing through a study of a 3-bit Flip Flop memory implementation. We delve into the entire modeling process, encompassing equations, task parametrization, and software development. The obtained networks are meticulously analyzed to elucidate dynamics, aided by an array of visualization and analysis tools. Moreover, the provided code is versatile enough to facilitate the modeling of diverse tasks and systems. Furthermore, we present how memory states can be efficiently stored in the vertices of a cube in the dimensionally reduced space, supplementing previous results with a distinct approach. | es |
| dc.description.fil | Fil: Jarne, Cecilia Gisele. Consejo Nacional de Investigaciones Científicas y Técnicas; Argentina. Universidad Nacional de Quilmes. Departamento de Ciencia y Tecnología; Argentina. University Aarhus; Dinamarca | |
| dc.format | application/pdf | es |
| dc.identifier.citation | Jarne, Cecilia Gisele; Exploring Flip Flop memories and beyond: training Recurrent Neural Networks with key insights; Frontiers Media; Frontiers in Systems Neuroscience; 18; 3-2024; 1-13 | es |
| dc.identifier.institucional | CONICET | |
| dc.identifier.issn | 1662-5137 | es |
| dc.identifier.repo | CONICET Digital | |
| dc.identifier.uri | http://hdl.handle.net/11336/232597 | |
| dc.journal.pagination | 1-13 | es |
| dc.journal.pais | Suiza | es |
| dc.journal.title | Frontiers in Systems Neuroscience | es |
| dc.journal.volume | 18 | es |
| dc.language.iso | eng | es |
| dc.publisher | Frontiers Media | es |
| dc.relation.alternativeid | info:eu-repo/semantics/altIdentifier/url/https://www.frontiersin.org/articles/10.3389/fnsys.2024.1269190/full | |
| dc.relation.alternativeid | info:eu-repo/semantics/altIdentifier/doi/http://dx.doi.org/10.3389/fnsys.2024.1269190 | |
| dc.rights | info:eu-repo/semantics/openAccess | * |
| dc.rights.uri | https://creativecommons.org/licenses/by-nc-sa/2.5/ar/ | * |
| dc.subject | RNNs | es |
| dc.subject | Flip Flps | es |
| dc.subject.classification | Otras Ciencias Físicas | es |
| dc.subject.classification | Ciencias Físicas | es |
| dc.subject.classification | CIENCIAS NATURALES Y EXACTAS | es |
| dc.title | Exploring Flip Flop memories and beyond: training Recurrent Neural Networks with key insights | es |
| dc.type | info:eu-repo/semantics/article | |
| dc.type | info:ar-repo/semantics/artículo | |
| dc.type | info:eu-repo/semantics/publishedVersion | |
Archivos
Bloque original
Cargando...
- Nombre:
- CONICET_Digital_Nro.d4d6b30e-1e42-443a-beee-69e2451946b6_B.pdf
- Tamaño:
- 3.03 MB
- Formato:
- Adobe Portable Document Format