Journal
FRONTIERS IN COMPUTATIONAL NEUROSCIENCE
Volume 10, Issue -, Pages -Publisher
FRONTIERS MEDIA SA
DOI: 10.3389/fncom.2016.00073
Keywords
connectionist modeling; unsupervised learning; deep neural networks; probabilistic generative models; computational neuropsychology
Funding
- European Research Council [210922]
- University of Padova (Strategic Grant NEURAT)
- European Research Council (ERC) [210922] Funding Source: European Research Council (ERC)
Ask authors/readers for more resources
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 of cognitive functions, which more faithfully reflect the underlying neural mechanisms at the same time providing a useful bridge to higher-level descriptions in terms of Bayesian computations. Here we discuss a powerful class of graphical models that can be implemented as stochastic, generative neural networks. These models overcome many limitations associated with classic connectionist models, for example by exploiting unsupervised learning in hierarchical architectures (deep networks) and by taking into account top-down, predictive processing supported by feedback loops. We review some recent cognitive models based on generative networks, and we point out promising research directions to investigate neuropsychological disorders within this approach. Though further efforts are required in order to fill the gap between structured Bayesian models and more realistic, biophysical models of neuronal dynamics, we argue that generative neural networks have the potential to bridge these levels of analysis, thereby improving our understanding of the neural bases of cognition and of pathologies caused by brain damage.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available