activity
20172021
most citedCompression and Interpretability of Deep Neural Networks via Tucker Tensor Layer: From First Principles to Tensor Valued Back-Propagation

21 citations · 26 across the 8 of their papers we have counts for

collaborators
Showing cs.LGShow all

2 papers · 1 filter

cs.LG2021

Tensor-Train Recurrent Neural Networks for Interpretable Multi-Way Financial Forecasting

Yao Lei Xu, Giuseppe G. Calvi, Danilo P. Mandic

Recurrent Neural Networks (RNNs) represent the de facto standard machine learning tool for sequence modelling, owing to their expressive power and memory. However, when dealing wit…

cs.LG2019★ 21 cited

Compression and Interpretability of Deep Neural Networks via Tucker Tensor Layer: From First Principles to Tensor Valued Back-Propagation

Giuseppe G. Calvi, Ahmad Moniri, Mahmoud Mahfouz +2

This work aims to help resolve the two main stumbling blocks in the application of Deep Neural Networks (DNNs), that is, the exceedingly large number of trainable parameters and th…