Cargando…
The Data Efficiency of Deep Learning Is Degraded by Unnecessary Input Dimensions
Biological learning systems are outstanding in their ability to learn from limited training data compared to the most successful learning machines, i.e., Deep Neural Networks (DNNs). What are the key aspects that underlie this data efficiency gap is an unresolved question at the core of biological a...
Autores principales: | D'Amario, Vanessa, Srivastava, Sanjana, Sasaki, Tomotake, Boix, Xavier |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Frontiers Media S.A.
2022
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8842477/ https://www.ncbi.nlm.nih.gov/pubmed/35173595 http://dx.doi.org/10.3389/fncom.2022.760085 |
Ejemplares similares
-
Recurrent connections facilitate symmetry perception in deep networks
por: Sundaram, Shobhita, et al.
Publicado: (2022) -
An efficient approach for textual data classification using deep learning
por: Alqahtani, Abdullah, et al.
Publicado: (2022) -
Multi-Feature Input Deep Forest for EEG-Based Emotion Recognition
por: Fang, Yinfeng, et al.
Publicado: (2021) -
A Space-Variant Visual Pathway Model for Data Efficient Deep Learning
por: Ozimek, Piotr, et al.
Publicado: (2019) -
An improved multi-input deep convolutional neural network for automatic emotion recognition
por: Chen, Peiji, et al.
Publicado: (2022)