activity
20242026
most citedInterpreting Deep Neural Network-Based Receiver Under Varying Signal-To-Noise Ratios

1 citations · 1 across the 4 of their papers we have counts for

collaborators
Showing 2024Show all

2 papers · 1 filter

cs.IT2024

Improving Numerical Stability of Normalized Mutual Information Estimator on High Dimensions

Marko Tuononen, Ville Hautamäki

Mutual information provides a powerful, general-purpose metric for quantifying the amount of shared information between variables. Estimating normalized mutual information using a…

cs.LG2024★ 1 cited

Interpreting Deep Neural Network-Based Receiver Under Varying Signal-To-Noise Ratios

Marko Tuononen, Dani Korpi, Ville Hautamäki

We propose a novel method for interpreting neural networks, focusing on convolutional neural network-based receiver model. The method identifies which unit or units of the model co…