Cargando…
Probabilistic Models and Generative Neural Networks: Towards an Unified Framework for Modeling Normal and Impaired Neurocognitive Functions
Connectionist models can be characterized within the more general framework of probabilistic graphical models, which allow to efficiently describe complex statistical distributions involving a large number of interacting variables. This integration allows building more realistic computational models...
Autores principales: | Testolin, Alberto, Zorzi, Marco |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Frontiers Media S.A.
2016
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4943066/ https://www.ncbi.nlm.nih.gov/pubmed/27468262 http://dx.doi.org/10.3389/fncom.2016.00073 |
Ejemplares similares
-
The Role of Architectural and Learning Constraints in Neural Network Models: A Case Study on Visual Space Coding
por: Testolin, Alberto, et al.
Publicado: (2017) -
Toward a unifying framework for the modeling and identification of motor primitives
por: Chiovetto, Enrico, et al.
Publicado: (2022) -
Probabilistic Encoding Models for Multivariate Neural Data
por: Triplett, Marcus A., et al.
Publicado: (2019) -
Neural oscillatory deficits in schizophrenia predict behavioral and neurocognitive impairments
por: Martínez, Antígona, et al.
Publicado: (2015) -
Learning Numerosity Representations with Transformers: Number Generation Tasks and Out-of-Distribution Generalization
por: Boccato, Tommaso, et al.
Publicado: (2021)