all AI news
An Attention Free Conditional Autoencoder For Anomaly Detection in Cryptocurrencies. (arXiv:2304.10614v1 [cs.LG])
cs.LG updates on arXiv.org arxiv.org
It is difficult to identify anomalies in time series, especially when there
is a lot of noise. Denoising techniques can remove the noise but this technique
can cause a significant loss of information. To detect anomalies in the time
series we have proposed an attention free conditional autoencoder (AF-CA). We
started from the autoencoder conditional model on which we added an
Attention-Free LSTM layer \cite{inzirillo2022attention} in order to make the
anomaly detection capacity more reliable and to increase the power …
anomaly anomaly detection arxiv attention autoencoder capacity cryptocurrencies denoising detection free identify information loss lstm noise power series time series