A bio-inspired bistable recurrent cell allows for long-lasting memory.
Recurrent neural networks (RNNs) provide state-of-the-art performances in a wide variety of tasks that require memory. These performances can often be achieved thanks to gated recurrent cells such as gated recurrent units (GRU) and long short-term memory (LSTM). Standard gated cells share a layer in...
Saved in:
Main Authors: | Nicolas Vecoven, Damien Ernst, Guillaume Drion |
---|---|
Format: | article |
Language: | EN |
Published: |
Public Library of Science (PLoS)
2021
|
Subjects: | |
Online Access: | https://doaj.org/article/9565af3b3b774e90a0d0dff60f3f8bc0 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Similar Items
-
Bio-inspired ultra-high energy efficiency bistable electronic billboard and reader
by: Weiran Zhang, et al.
Published: (2019) -
Optogenetics inspired transition metal dichalcogenide neuristors for in-memory deep recurrent neural networks
by: Rohit Abraham John, et al.
Published: (2020) -
Bio-inspired reversible underwater adhesive
by: Yanhua Zhao, et al.
Published: (2017) -
Bio-inspired self-shaping ceramics
by: Fabio L. Bargardi, et al.
Published: (2016) -
Exosomes: Novel Bio-Inspired Nanocarriers for Efficient Targeting of Glioblastoma Tumor Cells
by: V Taghdiri Nooshabadi, et al.
Published: (2021)