Cargando…
Robust high-dimensional memory-augmented neural networks
Traditional neural networks require enormous amounts of data to build their complex mappings during a slow training procedure that hinders their abilities for relearning and adapting to new data. Memory-augmented neural networks enhance neural networks with an explicit memory to overcome these issue...
Autores principales: | Karunaratne, Geethan, Schmuck, Manuel, Le Gallo, Manuel, Cherubini, Giovanni, Benini, Luca, Sebastian, Abu, Rahimi, Abbas |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Nature Publishing Group UK
2021
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8084980/ https://www.ncbi.nlm.nih.gov/pubmed/33927202 http://dx.doi.org/10.1038/s41467-021-22364-0 |
Ejemplares similares
-
Mixed-Precision Deep Learning Based on Computational Memory
por: Nandakumar, S. R., et al.
Publicado: (2020) -
Accelerating Inference of Convolutional Neural Networks Using In-memory Computing
por: Dazzi, Martino, et al.
Publicado: (2021) -
Experimental Demonstration of Supervised Learning in Spiking Neural Networks with Phase-Change Memory Synapses
por: Nandakumar, S. R., et al.
Publicado: (2020) -
Accurate deep neural network inference using computational phase-change memory
por: Joshi, Vinay, et al.
Publicado: (2020) -
Near-channel classifier: symbiotic communication and classification in high-dimensional space
por: Hersche, Michael, et al.
Publicado: (2021)