keyword : Out-of-distribution detection, metric learning, regularization, calibration

• Date

  2022.04.14

• Speaker

  김태욱

Topic:
Lockout : Sparse Regularization of Neural Networks

Keywords:
interpretable deep learning,
Neural network,
generalized model,
Feature selection,


Reference:
Valdes, Gilmer, et al. "…

• Date

  2022.04.08

• Speaker

  김현호

Keyword: meta-learning, reweighting, biased data

• Date

  2022-03-31

• Speaker

  이주형

Topic:
Transfer learning in manufacturing using artificial neural network: based on cases of injection molding and composites autoclave processing

Keywords:
Transfer learning
Sequential unfreezi…

• Date

  2022.03.31

• Speaker

  김주헌

KDD'21
SIGKDD Best paper of 2021 - Applied data science track

• Date

  2022.03.24

• Speaker

  이재민

- Introduction of One-class classification and Out-of-Distribution Detection

- "Entropic Out-of-Distribution Detection:Seamless Detection of Unknown Examples" paper review

- Proposal

• Date

  2022.03.02

• Speaker

  김태욱

Distance metric in high dimensionality

- When is "nearest neighobr" meaningful?

- On the surprising behavior of distance metrics in high dimensional space

• Date

  2022.03.02

• Speaker

  한민석

Simple and scalable sparse k-means clustering via feature ranking

- EM scheme 적용이 가능한 쉽고 빠른 k-means feature ranking 방법론

- High dimension에서, euclidean distance의 특징 및 분포에 관한 관찰

• Date

  2022.02.09

• Speaker

  한민석

Topic:
LassoNet : A Neural Network with Feature Sparsity

Keywords:
interpretable deep learning,
generalized model,
regression model,
variable selection,
Lasso

Reference:
Lemhadri, Ismael…

• Date

  2022.02.23

• Speaker

  김현호

Keywords: mixup, imbalance, data augmentation

1. mixup 소개 및 분석
2. mixup 관련 연구 소개
3. 새로운 방법론 제시 및 피드백

• Date

  2022-02-16

• Speaker

  이주형

Topic:
Transfer Learning with Dynamic Distribution Adaptation

Keywords:
Transfer learning
Domain adaptation
Distribution alignment
Deep learning
Subspace learning
Kernel method

Reference:…

• Date

  2022.02.09

• Speaker

  김주헌

keyword : Clustering, deep self-evolution clustering, self-evolution clustering training, deep unsupervised learning

• Date

  2022.02.09

• Speaker

  김태욱