This demo highlights how one can use a semi-supervised machine learning technique based on autoencoder to detect an anomaly in ... and the network consists of two parts: an encoder and a decoder.

First, to reduce the distance between multi-source homogeneous signals in the feature space, we design a novel Contrastive Pairs AutoEncoder (CPAE), which is for feature alignment before aggregating ...

This paper introduces GeneA-SLAM2, an RGB-D SLAM system for dynamic environments. It eliminates dynamic object interference via depth statistical information and enhances keypoint distribution ...

As a typical deep network, stacked autoencoder (SAE) has an outstanding modeling capability in soft sensors due to its ability to extract deep features. However, SAE ignores the expanded ...