Zobrazeno 1 - 10
of 72
pro vyhledávání: '"Macêdo, David"'
Autor:
Macêdo, David
Current deep learning solutions are well known for not informing whether they can reliably classify an example during inference. One of the most effective ways to build more reliable deep learning solutions is to improve their performance in the so-c
Externí odkaz:
http://arxiv.org/abs/2208.03566
Building robust deterministic neural networks remains a challenge. On the one hand, some approaches improve out-of-distribution detection at the cost of reducing classification accuracy in some situations. On the other hand, some methods simultaneous
Externí odkaz:
http://arxiv.org/abs/2205.05874
Publikováno v:
In Applied Soft Computing December 2024 167 Part A
Expressing and identifying emotions through facial and physical expressions is a significant part of social interaction. Emotion recognition is an essential task in computer vision due to its various applications and mainly for allowing a more natura
Externí odkaz:
http://arxiv.org/abs/2111.02273
Autor:
Macêdo, David, Ludermir, Teresa
Current out-of-distribution detection approaches usually present special requirements (e.g., collecting outlier data and hyperparameter validation) and produce side effects (e.g., classification accuracy drop and slow/inefficient inferences). Recentl
Externí odkaz:
http://arxiv.org/abs/2105.14399
Proper optimization of deep neural networks is an open research question since an optimal procedure to change the learning rate throughout training is still unknown. Manually defining a learning rate schedule involves troublesome time-consuming try a
Externí odkaz:
http://arxiv.org/abs/2102.08716
Autor:
Bajaj, Samridhi, Macedo, David S., Armendáriz-Vidales, Georgina, Conghaile, Peter Ó, Hogan, Conor F.
Publikováno v:
In Electrochimica Acta 20 January 2024 475
Autor:
Ayala, Angel, Fernandes, Bruno, Cruz, Francisco, Macêdo, David, Oliveira, Adriano L. I., Zanchettin, Cleber
Publikováno v:
2020 International Joint Conference on Neural Networks (IJCNN)
Most of the automatic fire alarm systems detect the fire presence through sensors like thermal, smoke, or flame. One of the new approaches to the problem is the use of images to perform the detection. The image approach is promising since it does not
Externí odkaz:
http://arxiv.org/abs/2008.06866
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 p
Externí odkaz:
http://arxiv.org/abs/2006.04005