Search Results for author: Teresa Ludermir

Found 12 papers, 3 papers with code

Metodos de Agrupamentos em dois Estagios

no code implementations2 Aug 2021 Jefferson Souza, Teresa Ludermir

This work investigates the use of two-stage clustering methods.

Otimizacao de pesos e funcoes de ativacao de redes neurais aplicadas na previsao de series temporais

no code implementations29 Jul 2021 Gecynalda Gomes, Teresa Ludermir

A methodology for the global optimization of this family of activation functions with free parameter and the weights of the connections between the processing units of the neural network is used.

Global Optimization Time Series +1

Otimizacao de Redes Neurais atraves de Algoritmos Geneticos Celulares

no code implementations18 Jul 2021 Anderson da Silva, Teresa Ludermir

This works proposes a methodology to searching for automatically Artificial Neural Networks (ANN) by using Cellular Genetic Algorithm (CGA).

Meta-aprendizado para otimizacao de parametros de redes neurais

no code implementations10 Jul 2021 Tarsicio Lucas, Teresa Ludermir, Ricardo Prudencio, Carlos Soares

In the current work, we performed a case study using meta-learning to choose the number of hidden nodes for MLP networks, which is an important parameter to be defined aiming a good networks performance.

Meta-Learning

Uso de GSO cooperativos com decaimentos de pesos para otimizacao de redes neurais

no code implementations5 Jul 2021 Danielle Silva, Teresa Ludermir

Training of Artificial Neural Networks is a complex task of great importance in supervised learning problems.

Global Optimization

Enhanced Isotropy Maximization Loss: Seamless and High-Performance Out-of-Distribution Detection Simply Replacing the SoftMax Loss

1 code implementation30 May 2021 David Macêdo, Teresa Ludermir

The entropic out-of-distribution detection solution uses the IsoMax loss for training and the entropic score for out-of-distribution detection.

Out-of-Distribution Detection

Training Aware Sigmoidal Optimizer

no code implementations17 Feb 2021 David Macêdo, Pedro Dreyer, Teresa Ludermir, Cleber Zanchettin

We compared the proposed approach with commonly used adaptive learning rate schedules such as Adam, RMSProp, and Adagrad.

Similarity Based Stratified Splitting: an approach to train better classifiers

no code implementations13 Oct 2020 Felipe Farias, Teresa Ludermir, Carmelo Bastos-Filho

We propose a Similarity-Based Stratified Splitting (SBSS) technique, which uses both the output and input space information to split the data.

Entropic Out-of-Distribution Detection: Seamless Detection of Unknown Examples

2 code implementations7 Jun 2020 David Macêdo, Tsang Ing Ren, Cleber Zanchettin, Adriano L. I. Oliveira, Teresa Ludermir

In this paper, we argue that the unsatisfactory out-of-distribution (OOD) detection performance of neural networks is mainly due to the SoftMax loss anisotropy and propensity to produce low entropy probability distributions in disagreement with the principle of maximum entropy.

General Classification Metric Learning +1

Isotropy Maximization Loss and Entropic Score: Accurate, Fast, Efficient, Scalable, and Turnkey Neural Networks Out-of-Distribution Detection Based on The Principle of Maximum Entropy

1 code implementation15 Aug 2019 David Macêdo, Tsang Ing Ren, Cleber Zanchettin, Adriano L. I. Oliveira, Teresa Ludermir

Consequently, we propose IsoMax, a loss that is isotropic (distance-based) and produces high entropy (low confidence) posterior probability distributions despite still relying on cross-entropy minimization.

Data Augmentation Metric Learning +1

Enhancing Batch Normalized Convolutional Networks using Displaced Rectifier Linear Units: A Systematic Comparative Study

no code implementations ICLR 2018 David Macêdo, Cleber Zanchettin, Adriano L. I. Oliveira, Teresa Ludermir

Besides, statistical significant performance assessments (p<0. 05) showed DReLU enhanced the test accuracy presented by ReLU in all scenarios.

Simple Fast Convolutional Feature Learning

no code implementations ICLR 2018 David Macêdo, Cleber Zanchettin, Teresa Ludermir

The quality of the features used in visual recognition is of fundamental importance for the overall system.

Cannot find the paper you are looking for? You can Submit a new open access paper.