The disclosed technology generally relates to outlier detection, and more particularly, to deep learning neural networks and devices and methods for detecting outliers using a non-transitory computer-readable storage medium. According to an embodiment, an outlier detection method using a deep learning neural network model includes providing a deep learning neural network model. The deep learning neural network model includes an encoder including a plurality of encoder layers and a decoder including a plurality of decoder layers. The method comprises feeding a first input to the encoder to generate a first encoded input and continuously processing the first input through the plurality of encoder layers-continuously processing the first input Further comprising-generating a first intermediate encoded input from one of the encoder layers prior to generating the first encoded input. The method further comprises feeding the first encoded input from the encoder to the decoder to produce a first reconstructed output and sequentially processing the first encoded input through the plurality of decoder layers. . The method comprises feeding the first reconstructed output from the decoder as a second or next input to the encoder and sequentially processing the first reconstructed output through the plurality of encoder layers-the first reconstructed The step of continuously processing the output further comprises-generating a second intermediate encoded input from one of the encoder layers. The method further includes detecting an outlier of the original input based on a comparison of the first intermediate encoded input and the second intermediate encoded input.
展开▼
