Learning fair representations by separating the relevance of potential information
T Quan, F Zhu, X Ling, Q Liu - Information Processing & Management, 2022 - Elsevier
… This section introduces the comparison methods used in the experiment. First, we
arranged a vanilla MLP to answer how much bias the model will produce without any …
arranged a vanilla MLP to answer how much bias the model will produce without any …
Explainable deep learning: A field guide for the uninitiated
… space of explainable deep learning for those in … deep learning, ii) discusses the evaluations
for model explanations, iii) places explainability in the context of other related deep learning …
for model explanations, iii) places explainability in the context of other related deep learning …
Equitable Artificial Intelligence for Glaucoma Screening with Fair Identity Normalization
… We designed a deep learning model based on the EfficientNet,37 enhanced with fair
identity … The incorporation of FIN with ResNet, as well as its comparison to oversampling and …
identity … The incorporation of FIN with ResNet, as well as its comparison to oversampling and …
FADES: Fair Disentanglement with Sensitive Relevance
… Learning fair representation in deep learning is essential to mitigate discriminatory … For
a fair comparison, we fixed the number of dimensions in the latent codes for all methods if …
a fair comparison, we fixed the number of dimensions in the latent codes for all methods if …
A deep learning approach to detection of splicing and copy-move forgeries in images
… For fair comparison, except for the first convolutional layer, other layer are all initialized
with “xavier”, and the involved two CNNs are trained through equal epochs. Fig.3 shows the …
with “xavier”, and the involved two CNNs are trained through equal epochs. Fig.3 shows the …
Mutual Information-Based Fair Active Learning
R Sonoda, R Srinivasan - ICASSP 2024-2024 IEEE …, 2024 - ieeexplore.ieee.org
… In this paper, we propose a fair active learning method that … when compared to existing
deep learning-based methods. … For fair comparison, the parameters both of Resnet18 and …
deep learning-based methods. … For fair comparison, the parameters both of Resnet18 and …
[图书][B] Comparative theology: Deep learning across religious borders
FX Clooney - 2010 - books.google.com
… actual instances of learning, specific experiments, deriving our insights from the actual
comparisons and not from a theory about religions or about the methodology of comparison. The …
comparisons and not from a theory about religions or about the methodology of comparison. The …
Learning fair representations through uniformly distributed sensitive attributes
… Thus, all of our other experiments are with a single level regularization for a fair comparison.
For this set of experiments, we trained the representation with higher weight (β = 1) on …
For this set of experiments, we trained the representation with higher weight (β = 1) on …
Towards Fair Video Summarization
… Recent advancements in deep learning have led to highly … and analytically define the fair
video summarization problem, … To ensure a fair comparison, we employ the same splits for …
video summarization problem, … To ensure a fair comparison, we employ the same splits for …
Deep learning using rectified linear units (relu)
AF Agarap - arXiv preprint arXiv:1803.08375, 2018 - arxiv.org
… used for the deep learning models used in the experiments. … standard datasets for
benchmarking deep learning models. It … for Fashion-MNIST for fair comparison. Though this …
benchmarking deep learning models. It … for Fashion-MNIST for fair comparison. Though this …