Topic:
Dynamic Curriculum Learning for Imbalanced Data Classification

Keywords:
Curriculum Learning
Class Imbalance
Sampling Strategy
Triplet Loss

Reference:
Wang, Y., Gan, W., Yang, J., …

• Date

  2024.07.31.

• Speaker

  변유정

Topic:
Correlation Recurrent Units A Novel Neural Architecture for Improving the Predictive Performance of Time-Series Data

Keywords:
Neural network
RNN
STL Decomposition

Reference:
Sim, Su…

• Date

  2024.07.30.

• Speaker

  김찬호

Topic:
Periodic activation function

Keywords:
Neural network
Periodicity
Activation function
Extrapolation

Reference:
Liu et al., “Neural Networks Fail to Learn Periodic Functions and How …

• Date

  2024.07.23

• Speaker

  김주헌

Topic:
What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?

keywords:
Semantic segmentation
Depth regression
Uncertainty estimation
Aleatoric uncertainty
epistemic unc…

• Date

  2024.07.23

• Speaker

  이형권

Topic:
Kolmogorov-Arnold Networks

Keywords:
Kolmogorov–Arnold representation theorem
MLP
Deep learning
Interpretability
Continual Learning

• Date

  2024.07.10

• Speaker

  김철규

Topic:
Recommender System

Keywords:
GNN
GC-MC
Message passing
Matrix Factorization

Reference:
Berg, Rianne van den, Thomas N. Kipf, and Max Welling. "Graph convolutional matrix completion.…

• Date

  2024.06.04.

• Speaker

  김찬호

Topic:
Missing imputation

Keywords:
Missing mechanism
Missing data handling
MICE (multiple imputation by chained equations)

Reference:
Azur et al., "Multiple imputation by chained equations…

• Date

  2024.05.14

• Speaker

  김주헌

Topic:
Bayesian Meta-Learning for the Few-Shot Setting via Deep Kernels

Keywords:
Bayesian Optimization
Few-Shot
Deep Kernels
Meta-Learning

• Date

  2024.04.02

• Speaker

  김철규

Topic :
Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization

Keywords:
Gradient-weighted class activation map
Visual Explanations
Localization Map

Reference:
1. …

• Date

  2024.03.19.

• Speaker

  김찬호

Topic :
Federated Bayesian Optimization via Thompson Sampling

Keywords:
Federated Learning
Bayesian Optimization
Random Fourier Features
Thompson Sampling
Federated Bayesian Optimization
Hyp…

• Date

  2024.04.02.

• Speaker

  구본영

Topic :
Debiased Causal Tree: Heterogeneous Treatment Effects Estimation with Unmeasured Confounding

Keywords:
Causal Inference
Heterogeneous Treatment Effects Estimation
Causal Tree
Confoundi…

• Date

  2024.02.29.

• Speaker

  변유정

Topic :
Tabular Data and Neural Nerworks

Keywords:
Deep tabular learning,
Numerical Feature embedding,



Reference:
1. Grinsztajn, Léo, Edouard Oyallon, and Gaël Varoquaux. "Why do tree-b…

• Date

  2024-02-29

• Speaker

  김현호