On the early diagnosis of Alzheimer's Disease from multimodal signals: A survey
Abstract Introduction The number of Alzheimer's Disease (AD) patients is increasing with
increased life expectancy and 115.4 million people are expected to be affected in 2050 …
increased life expectancy and 115.4 million people are expected to be affected in 2050 …
Early-learning regularization prevents memorization of noisy labels
We propose a novel framework to perform classification via deep learning in the presence of
noisy annotations. When trained on noisy labels, deep neural networks have been observed …
noisy annotations. When trained on noisy labels, deep neural networks have been observed …
Image classification with deep learning in the presence of noisy labels: A survey
Image classification systems recently made a giant leap with the advancement of deep
neural networks. However, these systems require an excessive amount of labeled data to be …
neural networks. However, these systems require an excessive amount of labeled data to be …
Deep self-learning from noisy labels
ConvNets achieve good results when training from clean data, but learning from noisy labels
significantly degrades performances and remains challenging. Unlike previous works …
significantly degrades performances and remains challenging. Unlike previous works …
Using trusted data to train deep networks on labels corrupted by severe noise
D Hendrycks, M Mazeika, D Wilson… - Advances in neural …, 2018 - proceedings.neurips.cc
The growing importance of massive datasets with the advent of deep learning makes
robustness to label noise a critical property for classifiers to have. Sources of label noise …
robustness to label noise a critical property for classifiers to have. Sources of label noise …
Training deep neural-networks using a noise adaptation layer
J Goldberger, E Ben-Reuven - International conference on learning …, 2022 - openreview.net
The availability of large datsets has enabled neural networks to achieve impressive
recognition results. However, the presence of inaccurate class labels is known to deteriorate …
recognition results. However, the presence of inaccurate class labels is known to deteriorate …
Learning from massive noisy labeled data for image classification
Large-scale supervised datasets are crucial to train convolutional neural networks (CNNs)
for various computer vision problems. However, obtaining a massive amount of well-labeled …
for various computer vision problems. However, obtaining a massive amount of well-labeled …
A survey of feature selection and feature extraction techniques in machine learning
Dimensionality reduction as a preprocessing step to machine learning is effective in
removing irrelevant and redundant data, increasing learning accuracy, and improving result …
removing irrelevant and redundant data, increasing learning accuracy, and improving result …
Classification in the presence of label noise: a survey
B Frénay, M Verleysen - IEEE transactions on neural networks …, 2013 - ieeexplore.ieee.org
Label noise is an important issue in classification, with many potential negative
consequences. For example, the accuracy of predictions may decrease, whereas the …
consequences. For example, the accuracy of predictions may decrease, whereas the …
Training convolutional networks with noisy labels
The availability of large labeled datasets has allowed Convolutional Network models to
achieve impressive recognition results. However, in many settings manual annotation of the …
achieve impressive recognition results. However, in many settings manual annotation of the …