no code implementations • 10 Oct 2023 • Diego Marcondes, Junior Barrera
The machine learning of lattice operators has three possible bottlenecks.
1 code implementation • 6 Oct 2023 • Diego Marcondes, Mariana Feldman, Junior Barrera
We also proposed a stochastic lattice descent algorithm (SLDA) to learn the parameters of Canonical Discrete Morphological Neural Networks (CDMNN), whose architecture is composed only of operators that can be decomposed as the supremum, infimum, and complement of erosions and dilations.
1 code implementation • 1 Sep 2023 • Diego Marcondes, Junior Barrera
We propose the Discrete Morphological Neural Networks (DMNN) for binary image analysis to represent W-operators and estimate them via machine learning.
no code implementations • 31 Oct 2022 • Diego Marcondes, Adilson Simonis, Junior Barrera
Science consists on conceiving hypotheses, confronting them with empirical evidence, and keeping only hypotheses which have not yet been falsified.
no code implementations • 8 Sep 2021 • Diego Marcondes, Adilson Simonis, Junior Barrera
This paper proposes a data-driven systematic, consistent and non-exhaustive approach to Model Selection, that is an extension of the classical agnostic PAC learning model.
1 code implementation • 24 Apr 2020 • Gustavo Estrela, Marco D. Gubitoso, Carlos E. Ferreira, Junior Barrera, Marcelo S. Reis
It consists of finding a subset of features that is optimum for a given cost function.
no code implementations • 30 Jan 2020 • Diego Marcondes, Adilson Simonis, Junior Barrera
In this paper, we carry further our agenda, by showing the consistency of a model selection framework based on Learning Spaces, in which one selects from data the Hypotheses Space on which to learn.
no code implementations • 26 Jan 2020 • Diego Marcondes, Adilson Simonis, Junior Barrera
A remarkable, formally proved, consequence of this approach are conditions on $\mathbb{L}(\mathcal{H})$ and on the loss function that lead to estimated out-of-sample error surfaces which are true U-curves on $\mathbb{L}(\mathcal{H})$ chains, enabling a more efficient search on $\mathbb{L}(\mathcal{H})$.
no code implementations • 11 Nov 2017 • Diego Marcondes, Adilson Simonis, Junior Barrera
The main contribution of this paper is to define and apply this local measure, which permits to analyse local properties of joint distributions that are neglected by the classical Shanon's global measure.
1 code implementation • 19 Jul 2017 • Marcelo S. Reis, Gustavo Estrela, Carlos E. Ferreira, Junior Barrera
In this paper, we introduce featsel, a framework for benchmarking of feature selection algorithms and cost functions.
no code implementations • 22 Jul 2014 • Marcelo S. Reis, Carlos E. Ferreira, Junior Barrera
The U-curve optimization problem is characterized by a decomposable in U-shaped curves cost function over the chains of a Boolean lattice.