Model Reduction Through Progressive Latent Space Pruning in Deep Active Inference

Although still not fully understood, sleep is known to play an important role in learning and in pruning synaptic connections. From the active inference perspective, this can be cast as learning parameters of a generative model and Bayesian model reduction, respectively. In this article, we show how...

Full description

Bibliographic Details
Main Authors:	Çatal, O. (Author), De Boom, C. (Author), Dhoedt, B. (Author), Verbelen, T. (Author), Wauthier, S.T (Author)
Format:	Article
Language:	English
Published:	Frontiers Media S.A. 2022
Subjects:	active inference Active inference article Bayesian modelling Bayesian networks Complex networks deep learning Deep learning deep neural network Deep neural networks Economic and social effects free energy Free energy Generative model generative modeling Inference perspectives Learning parameters model reduction Model reduction Modeling complexity Modeling performance simulation sleep Synaptic connections
Online Access:	View Fulltext in Publisher

Internet

View Fulltext in Publisher

Model Reduction Through Progressive Latent Space Pruning in Deep Active Inference

Internet

Similar Items