Search Results for author:
Found 14 papers, 4 papers with code
Enhancing Batch Normalized Convolutional Networks using Displaced Rectifier Linear Units: A Systematic Comparative Study
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
The quality of the features used in visual recognition is of fundamental importance for the overall system.
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
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.
Entropic Out-of-Distribution Detection: Seamless Detection of Unknown Examples
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.
Similarity Based Stratified Splitting: an approach to train better classifiers
We propose a Similarity-Based Stratified Splitting (SBSS) technique, which uses both the output and input space information to split the data.
Training Aware Sigmoidal Optimizer
We compared the proposed approach with commonly used adaptive learning rate schedules such as Adam, RMSProp, and Adagrad.
Improving Entropic Out-of-Distribution Detection using Isometric Distances and the Minimum Distance Score
The entropic out-of-distribution detection solution comprises the IsoMax loss for training and the entropic score for out-of-distribution detection.
Enhanced Isotropy Maximization Loss: Seamless and High-Performance Out-of-Distribution Detection Simply Replacing the SoftMax Loss
The IsoMax loss works as a drop-in replacement of the SoftMax loss (i. e., the combination of the output linear layer, the SoftMax activation, and the cross-entropy loss) because swapping the SoftMax loss with the IsoMax loss requires no changes in the model's architecture or training procedures/hyperparameters.
Uso de GSO cooperativos com decaimentos de pesos para otimizacao de redes neurais
Training of Artificial Neural Networks is a complex task of great importance in supervised learning problems.
Meta-aprendizado para otimizacao de parametros de redes neurais
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.
Otimizacao de Redes Neurais atraves de Algoritmos Geneticos Celulares
This works proposes a methodology to searching for automatically Artificial Neural Networks (ANN) by using Cellular Genetic Algorithm (CGA).
Otimizacao de pesos e funcoes de ativacao de redes neurais aplicadas na previsao de series temporais
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.
Metodos de Agrupamentos em dois Estagios
This work investigates the use of two-stage clustering methods.
Distinction Maximization Loss: Efficiently Improving Out-of-Distribution Detection and Uncertainty Estimation by Replacing the Loss and Calibrating
In this paper, we propose training deterministic neural networks using our DisMax loss, which works as a drop-in replacement for the usual SoftMax loss (i. e., the combination of the linear output layer, the SoftMax activation, and the cross-entropy loss).
