Learning from imperfect data for anomaly detection
AssigneeNokia Solutions and Networks Oy
InventorsMohamed Trabelsi, Ahmet Akyamac
Life of this patent
Estimating the term…
Loading patent…
AssigneeNokia Solutions and Networks Oy
InventorsMohamed Trabelsi, Ahmet Akyamac
Estimating the term…
Apparatus and method of training Machine Learning (ML) models. In an embodiment, the apparatus performs initial training of an anomaly detection model based on training samples of a training dataset over multiple epochs, where the anomaly detection model comprises a variational autoencoder (VAE). For each training sample during an epoch, the initial training comprises inputting an original data sequence of the training sample into the VAE encoder to output a multivariant distribution in latent space, sampling the multivariant distribution to generate multiple latent vectors, inputting the latent vectors into the VAE decoder to output reconstructed data sequences, and computing an estimated sample weight for the training sample. The apparatus identifies, after multiple epochs, corrupted samples from the training dataset based on the estimated sample weights, removes the corrupted samples to generate a filtered training dataset, and performs final training of the anomaly detection model based on the filtered training dataset.
An apparatus, comprising:
A method comprising:
A computer readable medium embodying programmed instructions which, when executed by a processor, are operable for performing a method comprising:
Dependencies are inferred from the claim text.