no code implementations • 8 Dec 2023 • Dani Korpi, Mikko Honkala, Janne M. J. Huttunen
This paper investigates the feasibility of machine learning (ML)-based pilotless spatial multiplexing in multiple-input and multiple-output (MIMO) communication systems.
no code implementations • 16 Feb 2022 • Janne M. J. Huttunen, Dani Korpi, Mikko Honkala
The main task of the neural network is to predict the channel evolution between uplink and downlink slots, but it can also learn to handle inefficiencies and errors in the whole chain, including the actual beamforming phase.
no code implementations • 14 Jan 2022 • Dani Korpi, Mikko Honkala, Janne M. J. Huttunen, Fayçal Ait Aoudia, Jakob Hoydis
In particular, we consider a scenario where the transmitter power amplifier is operating in a nonlinear manner, and ML is used to optimize the waveform to minimize the out-of-band emissions.
no code implementations • 30 Jun 2021 • Jaakko Pihlajasalo, Dani Korpi, Mikko Honkala, Janne M. J. Huttunen, Taneli Riihonen, Jukka Talvitie, Alberto Brihuega, Mikko A. Uusitalo, Mikko Valkama
In this paper, we propose a machine learning (ML) based physical layer receiver solution for demodulating OFDM signals that are subject to a high level of nonlinear distortion.
no code implementations • 30 Oct 2020 • Dani Korpi, Mikko Honkala, Janne M. J. Huttunen, Vesa Starck
Recently, deep learning has been proposed as a potential technique for improving the physical layer performance of radio receivers.
no code implementations • 4 May 2020 • Mikko Honkala, Dani Korpi, Janne M. J. Huttunen
To this end, we propose a deep fully convolutional neural network, DeepRx, which executes the whole receiver pipeline from frequency domain signal stream to uncoded bits in a 5G-compliant fashion.
1 code implementation • 6 Dec 2016 • Francesco Cricri, Xingyang Ni, Mikko Honkala, Emre Aksu, Moncef Gabbouj
Thanks to the recurrent connections, the decoder can exploit temporal summaries generated from all layers of the encoder.
no code implementations • NeurIPS 2015 • Mathias Berglund, Tapani Raiko, Mikko Honkala, Leo Kärkkäinen, Akos Vetek, Juha T. Karhunen
Although unidirectional RNNs have recently been trained successfully to model such time series, inference in the negative time direction is non-trivial.
10 code implementations • NeurIPS 2015 • Antti Rasmus, Harri Valpola, Mikko Honkala, Mathias Berglund, Tapani Raiko
We combine supervised learning with unsupervised learning in deep neural networks.
no code implementations • NeurIPS 2015 • Mathias Berglund, Tapani Raiko, Mikko Honkala, Leo Kärkkäinen, Akos Vetek, Juha Karhunen
Although unidirectional RNNs have recently been trained successfully to model such time series, inference in the negative time direction is non-trivial.