Romis Attux

TL;DR: A new method for extracting discriminative features according to the Fourier analysis can be combined with deep architectures in order to improve image classification and raise the discussion on how frequency domain layers can be used in deep architectures to further improve the network performance.

TL;DR: A comparative investigation regarding the performances of a classic ELM and ESNs in the context of the prediction of monthly seasonal streamflow series associated with Brazilian hydroelectric plants shows the relevance of these architectures in modeling seasonal stream flow series.

TL;DR: A comparative investigation between the performances of different ESNs in the context of the forecasting of seasonal streamflow series associated with Brazilian hydroelectric plants shows the relevance of these networks and also contributes to a better understanding of their applicability to forecasting problems.

TL;DR: This work proposes novel strategies for ESN reservoir design based on the theoretical framework built by Kohonen׳s classical works on self-organization – which includes the notions of short-range positive feedback and lateral inhibition – and also on the related and more recent notion of neural gas.

TL;DR: A systematic analysis of a game controlled by a Brain-Computer Interface (BCI) based on Steady-State Visually Evoked Potentials (SSVEP) shows the feasibility of the direct communication between the brain and the computer.