No abstract

We study Bayesian hypernetworks: a framework for approximate Bayesian inference in neural networks. A Bayesian hypernetwork h is a neural network which learns to transform a simple noise distribution, p( ) = N (0, I), to a distribution q(θ) := q(h( )) over the parameters θ of another neural network (the "primary network"). We train q with variational inference, using an invertible h to enable efficient estimation of the variational lower bound on the posterior p(θ|D) via sampling. In contrast to most methods for Bayesian deep learning, Bayesian hypernets can represent a complex multimodal approximate posterior with correlations between parameters, while enabling cheap iid sampling of q(θ). In practice, Bayesian hypernets can provide a better defense against adversarial examples than dropout, and also exhibit competitive performance on a suite of tasks which evaluate model uncertainty, including regularization, active learning, and anomaly detection.

Our findings suggest that activation of p-Drp1(Ser616) is related to seizure-induced neuronal damage. Modulation of p-Drp1(Ser616) expression is accompanied by decreases in mitochondrial fission, mitochondrial dysfunction, and oxidation, providing a neuroprotective effect against seizure-induced hippocampal neuronal damage.

No abstract

No abstract