collaborators

5 papers

eess.SP2026

Input-Correlated Supervision Noise Limits the Benefits of OTA Training for Learned Receivers

Riku Luostari, Dani Korpi, Olav Tirkkonen +1

While learned wireless receivers are typically studied using synthetic data, the impact of over-the-air (OTA) measurements for training remains unclear. We conducted a 5.88 GHz mea…

eess.SP2026

EqDeepRx: Learning a Scalable and Interference Mitigating MIMO Receiver

Mikko Honkala, Dani Korpi, Elias Raninen +1

While machine learning (ML)-based receiver algorithms have received a great deal of attention in the recent literature, they often suffer from poor scaling with increasing spatial…

cs.LG2026

Out-of-Distribution Detection via Channelwise Feature Aggregation in Neural Network-Based Receivers

Marko Tuononen, Heikki Penttinen, Duy Vu +3

Neural network-based radio receivers are expected to play a key role in future wireless systems, making reliable Out-Of-Distribution (OOD) detection essential. We propose a post-ho…

eess.SP2025

Demonstrating Interoperable Channel State Feedback Compression with Machine Learning

Dani Korpi, Rachel Wang, Jerry Wang +20

Neural network-based compression and decompression of channel state feedback has been one of the most widely studied applications of machine learning (ML) in wireless networks. Var…

cs.LG2025

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…