IEEE

Graph-based Multiscale Stacked Autoencoder for Biopharmaceutical Processes Soft Sensor

Abstract: Accurate monitoring of key process variables is essential for biopharmaceutical manufacturing, but the direct measurements are often costly and involve substantial time delays. Data-driven ...
IEEE

Learning Robust Representations by Autoencoders With Dynamical Implicit Mapping

Abstract: Autoencoder is an unsupervised neural network that learns effective representations of data and has wide applications in feature learning, data compression, etc. However, Autoencoder is very ...
Scientific Research Publishing

A Combination Method of Stacked Convolutional Auto-Encoder and Selective Kernel Attention Mechanism for Image Classification ()

1 College of Information Engineering, Xinchuang Software Industry Base, Yancheng Teachers University, Yancheng, China. 2 Yancheng Agricultural College, Yancheng, China. Convolutional auto-encoders ...
GitHub

Deprocessing args cause error in convert

Correction: this works if the image_output_names is set correctly. However, it would be nice to be able to rename the image output instead of having to match it. When converting to ONNX as an ...
GitHub

Variational autoencoder

Train a Variational Auto-encoder using facenet-based perceptual loss similar to the paper "Deep Feature Consistent Variational Autoencoder". Calculate attribute vectors based on the attributes in the ...