On Mixup Training: Improved Calibration and Predictive Uncertainty for deep Neural Networks Keyword : Calibration, Uncertainty, mix-up
2022.10.06
김태욱
Topic: Certified Monotonic Neural Networks Keywords: interpretable deep learning, Model generalization Neural network, Monotonicity, Reference: Liu, Xingchao, et al. "Certified monotonic…
2022-09-29
김현호
TabNet: Attentive Interpretable Tabular Learning
2022.02.22
윤재섭
Keywords: pruning, initialization, subspace 적은 수의 파라미터를 가진 pruned model이 덜 학습하여도 original network 보다 좋은 performance를 보여줄 수 있다.
2022-06-23
이주형
Topic: How Domain Adaptation Works Keywords: Domain adaptation Transfer learning Learning theory Sample-selection bias Reference: S. Ben-David, J. Blitzer, K. Crammer, A. Kulesza, F. Perei…
2022.06.23
김주헌
Importance Estimation for Neural Network Pruning
2022.06.09
김태흥
1. Discriminative feature space embedding using angular margin loss 2. Separate Maximum softmax probability score between ID and OOD using weight decay regularization keywords : Out-of-distributio…
05/26
Adjusting existing models for regional drift VFDT / CVFDT - A decision tree induction system capable of learning from high-speed data streams in an incremental, anytime fashion. - Extension t…
2022-05-26
한민석
Topic: Neural Additive Models: Interpretable Machine Learning with Neural Nets Keywords: generalized additive model, interpretable deep learning, Neural network, Reference: Agarwal, Ris…
2022-05-18
Keywords: data shift, data augmentation, robustness, uncertainty 1. 데이터의 작은 변화에도 모델의 예측 결과는 크게 변화 (Data Shift) 2. 다양한 augmentation 기법을 연쇄적으로 적용하고 mixup 3. 모델의 clean accuracy, robustness, uncerta…
2022-05-12
CLeaR: An adaptive continual learning framework for regression tasks Regression 문제에 대한 New Task / Catastrophic forgetting의 정의 이를 해결하기 위한 Framework 제안
2022-04-28
기존 제약식 기반에서 로스함수 기반으로 변경 4개의 실제 데이터셋에 대한 실험 추가
Fair Clustering Through Fairlets Chierichetti, Flavio, et al. "Fair clustering through fairlets." Advances in Neural Information Processing Systems 30 (2017).
2022.04.14
keyword : Out-of-distribution detection, metric learning, regularization, calibration
Imbalanced dataset classification - Baseline methods
2022.04.07