[meta] (paper 15) Meta-Learning with Latent Embedding Optimization
2019
Paper Reading Study
[meta] (paper 12) Learning to Balance ; Bayesian Meta Learning for Imbalanced and Out-of-distribution Tasks
Learning to Balance ; Bayesian Meta Learning for Imbalanced and Out-of-distribution Tasks
[meta] (paper 11) Online Meta-Learning
Online Learning, Meta Learning
[meta] (paper 10) Meta Learning Probabilistic Inference For Prediction
Meta Learning Probabilistic Inference For Prediction
[meta] (paper 9) Meta-Weight-Net ; Learning an Explicit Mapping For Sampling Weighting
Meta-Weight-Net
[meta] (paper 8) Amortized Bayesian Meta-Learning
Amortized Bayesian Meta Learning
[meta] (code review) Matching Networks
Matching Networks, Pytorch
[cs330] (4강) Non-parametric Meta-Learners
CS330 Multi-task and Meta Learning 강의
[continual] (paper 7) Variational Continual Learning
Variational Continual Learning (VCL)
[meta] (paper 7) Learning to Propagate Labels ; Transductive Propagation Network for Few shot Learning
TPN, Label Propagation
[cs330] (3강) Optimization-based Meta Learning
CS330 Multi-task and Meta Learning 강의
[continual] (paper 8) Progress & Compress ; A scalable framework for continual learning
Progress & Compress ; A scalable framework for continual learning
[meta] (paper 6) On First Order Meta Learning Algorithms
MAML, FOMAML, Reptile
[cs330] (2강) Multi-Task Learning, Transfer Learning Basics
CS330 Multi-task and Meta Learning 강의
[meta] (paper 5) Prototypical Networks for Few shot Learning
2017, Prototypical Networks
[continual] (paper 6) Lifelong Learning with Dynamically Expandable Networks
Dynamically Expandable Networks (DEN)
[continual] (paper 4) Continual Learning with Deep Generative Replay
Deep Generative Replay
[meta] (paper 3) Towards a Neural Statistician
2016, VAE, Statistic Network
[continual] (paper 3) Overcoming catastrophic forgetting by incremental moment matching
Catastrophic Forgetting, IMM, Mean-IMM, Mode-IMM
[meta] (paper 2) Matching Networks for One Shot Learning
2016, Matching Networks
[continual] (paper 2) Overcoming catastrophic forgetting in neural networks
Catastrophic Forgetting, EWC
[reliable] (paper 8) Can You Trust Your Model’s Uncertainty\? Evaluating Predictive Uncertainty Under Data Shift
Can You Trust Your Model’s Uncertainty? Evaluating Predictive Uncertainty Under Data Shift
[reliable] (paper 6) A Simple Baseline for Bayesian Uncertainty in Deep Learning
Deep Learning Uncertainty, Deep Ensembles, Predictive Uncertainty
[reliable] (paper 5) Accurate Uncertainties for Deep Learning Using Calibrated Regression
Deep Learning Uncertainty, Deep Ensembles, Predictive Uncertainty
[reliable] (paper 4) Training Confidence-calibrated Classifiers for Detecting Out-of-Distribution Samples
Confidence-calibrated Classifiers, Out-of-Distribution
[reliable] (paper 3) Enhancing the Reliability of Out-of-distribution Image detection in Neural Networks
ODIN, Out-of-distribution detection
[reliable] (paper 2) Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles
Deep Learning Uncertainty, Deep Ensembles, Predictive Uncertainty
[reliable] (paper 1) On Calibration of Modern Neural Networks
Deep Learning Uncertainty, Calibration
[interpretable] (paper 6) Neural Additive Models ; Interpretable Machine Learning with Neural Nets
NAMs
[interpretable] (paper 5) Towards Automatic Concept-based Explanations
Towards Automatic Concept-based Explanations
study(paper 4)uncertainty Aware attention for reliable interpretation and prediction
Attention mechanism
[interpretable] (paper 1) Why Should I Trust You? Explaining the Predictions of Any Classifier
LIME (Local Interpretable Model-agnostic Explanations)
[continual] (paper 1) Progressive Neural Network
Progressive Neural Network에 관한 소개글
[continual] Continual Learning 소개
Continual Learning에 대한 소개글
[meta] Meta Learning 소개
Meta Learning에 대한 소개글