Dendrites endow artificial neural networks with accurate, robust and parameter-efficient learning
Abstract Artificial neural networks (ANNs) are at the core of most Deep Learning (DL) algorithms that successfully tackle complex problems like image recognition, autonomous driving, and natural language processing. However, unlike biological brains who tackle similar problems in a very efficient ma...
Saved in:
| Main Authors: | Spyridon Chavlis, Panayiota Poirazi |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-01-01
|
| Series: | Nature Communications |
| Online Access: | https://doi.org/10.1038/s41467-025-56297-9 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Similar Items
-
An Efficient Dropout for Robust Deep Neural Networks
by: Yavuz Çapkan, et al.
Published: (2025-07-01) -
Artificial neural network accurately predicts hepatitis B surface antigen seroclearance.
by: Ming-Hua Zheng, et al.
Published: (2014-01-01) -
Accurate and Efficient LiDAR SLAM by Learning Unified Neural Descriptors
by: Baihe Feng, et al.
Published: (2025-01-01) -
Simulation and accurate prediction of thermal efficiency of functionalized COOH-MWCNT/water nanofluids by artificial neural network using experimental data
by: Mohammad Hemmat Esfe, et al.
Published: (2025-01-01) -
Accurate Prediction of Compression Index of Normally Consolidated Soils Using Artificial Neural Networks
by: Ali Ulvi Uzer
Published: (2024-08-01)