Comparison of RNN Encoder-Decoder Models for Anomaly Detection

TL;DR

This study compares various RNN Encoder-Decoder models for anomaly detection, finding that restoring the current sequence yields better performance than predicting future sequences, based on experiments with simple vector datasets.

Contribution

It provides an empirical comparison of RNN Encoder-Decoder models focusing on sequence restoration versus prediction for anomaly detection.

Findings

Restoring current sequences outperforms predicting future sequences.

Model performance is consistent across different parameters and optimizers.

Simple vector datasets are effective for experimental validation.

Abstract

In this paper, we compare different types of Recurrent Neural Network (RNN) Encoder-Decoders in anomaly detection viewpoint. We focused on finding the model that can learn the same data more effectively. We compared multiple models under the same conditions, such as the number of parameters, optimizer, and learning rate. However, the difference is whether to predict the future sequence or restore the current sequence. We constructed the dataset with simple vectors and used them for the experiment. Finally, we experimentally confirmed that the model performs better when the model restores the current sequence, rather than predict the future sequence.