Sparse AutoGrad: A Custom Automatic Differentiation Library A from-scratch implementation of automatic differentiation with sparse training capabilities, featuring a complete neural network framework ...

The autoencoder (AE) is a fundamental deep learning approach to anomaly detection. AEs are trained on the assumption that abnormal inputs will produce higher reconstruction errors than normal ones. In ...

Autoencoder Model A convolutional autoencoder is trained to predict differences between frames. The encoder extracts compressed features, while the decoder reconstructs frame differences. Model ...