Search Results for author:
Found 5 papers, 3 papers with code
Understanding CNN Fragility When Learning With Imbalanced Data
To demystify CNN decisions on imbalanced data, we focus on their latent features.
Towards A Holistic View of Bias in Machine Learning: Bridging Algorithmic Fairness and Imbalanced Learning
A key element in achieving algorithmic fairness with respect to protected groups is the simultaneous reduction of class and protected group imbalance in the underlying training data, which facilitates increases in both model accuracy and fairness.
Efficient Augmentation for Imbalanced Deep Learning
We empirically study a convolutional neural network's internal representation of imbalanced image data and measure the generalization gap between a model's feature embeddings in the training and test sets, showing that the gap is wider for minority classes.
Developing an NLP-based Recommender System for the Ethical, Legal, and Social Implications of Synthetic Biology
This text proposes a different approach, asking instead is it possible to develop a well-performing recommender model based upon natural language processing (NLP) to connect synthetic biologists with information on the ELSI of their specific research?
DeepSMOTE: Fusing Deep Learning and SMOTE for Imbalanced Data
An important advantage of DeepSMOTE over GAN-based oversampling is that DeepSMOTE does not require a discriminator, and it generates high-quality artificial images that are both information-rich and suitable for visual inspection.
