Cargando…
Efficient neural codes naturally emerge through gradient descent learning
Human sensory systems are more sensitive to common features in the environment than uncommon features. For example, small deviations from the more frequently encountered horizontal orientations can be more easily detected than small deviations from the less frequent diagonal ones. Here we find that...
Autores principales: | Benjamin, Ari S., Zhang, Ling-Qi, Qiu, Cheng, Stocker, Alan A., Kording, Konrad P. |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Nature Publishing Group UK
2022
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9800366/ https://www.ncbi.nlm.nih.gov/pubmed/36581618 http://dx.doi.org/10.1038/s41467-022-35659-7 |
Ejemplares similares
-
On Scalable Deep Learning and Parallelizing Gradient Descent
por: Hermans, Joeri
Publicado: (2017) -
Neural spiking for causal inference and learning
por: Lansdell, Benjamin James, et al.
Publicado: (2023) -
Efficient Sensor Placement Optimization Using Gradient Descent and Probabilistic Coverage
por: Akbarzadeh, Vahab, et al.
Publicado: (2014) -
Machine Learning for Neural Decoding
por: Glaser, Joshua I., et al.
Publicado: (2020) -
Mutual Information Based Learning Rate Decay for Stochastic Gradient Descent Training of Deep Neural Networks
por: Vasudevan, Shrihari
Publicado: (2020)