9 papers
Exponential Noise Robustness of Type-Based Multiple Access for Over-the-Air Computation
Marc Martinez-Gost, Ana Pérez-Neira, Miguel Ãngel Lagunas
This paper studies the robustness of type-based multiple access (TBMA) in over-the-air computation (AirComp) under nonparametric estimation, where no prior knowledge of the data di…
The DCT Model as a Novel Regression Framework within a Lagrangian Formulation
Marc Martinez-Gost, Ana I. Perez Neira, Miguel Angel Lagunas
This paper introduces a unified regression framework based on the Lagrange formalism, demonstrating how polynomial and logistic regression can all be formulated within a common var…
The DCT Neuron for Estimation and Compensation of Amplitude Distortions in OFDM Systems
Marc Martinez-Gost, Ana Pérez-Neira, Miguel Ãngel Lagunas
We present a receiver-side framework for identifying amplitude distortions in frequency-selective OFDM channels. The core novelty is the use of the DCT Neuron, a compact adaptive p…
Efficient Neural Networks with Discrete Cosine Transform Activations
Marc Martinez-Gost, Sara Pepe, Ana Pérez-Neira +1
In this paper, we extend our previous work on the Expressive Neural Network (ENN), a multilayer perceptron with adaptive activation functions parametrized using the Discrete Cosine…
Before AI Takes Over: Rethinking Nonlinear Signal Processing in Communications
Ana Pérez-Neira, Marc Martinez-Gost, Miguel Ãngel Lagunas
There is an urgent reflection on traditional nonlinear signal processing methods in communications before Artificial Intelligence (AI) dominates the field. It implies a need to rea…
Waveforms for Computing Over the Air
Ana Pérez-Neira, Marc Martinez-Gost, Alphan Åahin +3
Over-the-air computation (AirComp) leverages the signal-superposition characteristic of wireless multiple access channels to perform mathematical computations. Initially introduced…