3D convolutional and recurrent neural networks for reactor perturbation unfolding and anomaly detection

Euratom Research and Training in 2019: the Awards collection

Open Access

Fig. 5

LSTM RNN architecture proposed for the classification task, outputting a 512-dimensional representational vector of the input to a 6-unit classification layer. The LSTM units take in input from the bottom, x _t, with all gates depicted in each LSTM cell.

Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.

Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.

Initial download of the metrics may take a while.