Our method offers a good trade-off between the number of parameters and classification accuracy.
Ranked #1 on Image Classification on Fashion-MNIST
With a single epoch of training, our method improves the AUC by 8. 03% compared to the convolutional LSTM-based approach.
The better accuracy and complexity compromise, as well as the extremely fast speed of our method makes it suitable for neural network compression.
In this paper, we define rank selection as a combinatorial optimization problem and propose a methodology to minimize network complexity while maintaining the desired accuracy.