Coder Social home page Coder Social logo

ai-study's Introduction

AI-Study

인공지능 논문 스터디

1. 스터디 안내

  • 일시: 매주 수요일 9:00 PM
  • 내용: 연구 주제 발표 및 논문 리뷰
  • 목적: 다양한 분야의 최신 트렌드 파악 및 AI 지식 저변 확대

2. 스터디 멤버

  • 임진혁: Knowledge Distillation, Meta Learning, Few Shot Learning, Self-supervised Learning, Domain Generalization, Federate Learning
  • 최영제: Machine Learning, Reinforcement Learning, Auto Feature Engineering, Time Series Forecasting, Anomaly Detection

Paper List

Date Paper Topic Presenter Links Needs futher modification
2020.04.16 [CVPR 2019] SpotTune, Transfer learning through adaptive fine-tuning Vision, Transfer Learning 최영제 paper
review
blog
X
2020.04.23 [NIPS 2015] Distilling the Knowledge in a Neural Network Knowledge Distillation 임진혁 paper
review
O
2020.05.14 [CVPR 2019] Class-Balanced Loss Based on Effective Number of Samples Class Imbalance 최영제 paper
review
blog
X
2020.05.20 [KDD 2018] Ranking Distillation: Learning Compact Ranking Models With High Performance for Recommender System Recommeder System
Knowledge Distillation
임진혁 paper
review
O
2020.07.02 [NIPS 2019] Shape and Time Distortion Loss for Training Deep Time Series Forecasting Models Time Series Forecasting 최영제 paper
review
X
2020.07.08 [ICML 2020] Rethinking Data Augmentation: Self-Supervision and Self-Distillation Augmentation
Self-Supervised Learning
임진혁 paper
review
O
2020.07.16 [ICLR 2020] Distance based learning from errors for confidence calibration Model Calibration 최영제 paper
review
blog
X
2020.07.23 [NIPS 2019] Knowledge Extraction with No Observable Data Knowledge Disillation 임진혁 paper
review
O
2021.02.25 [NIPS 2020] Self-supervised Auxiliary Learning with Meta-paths for Heterogeneous Graphs GNN
Self-Supervised Learning
임진혁 paper
review
O
2021.02.25 [ICML 2018] GAIN Missing Data Imputation using Generative Adversarial Nets Data Imputation 최영제 paper
review
blog
X
2021.03.04 [AISTATS 2017] Communication-Efficient Learning of Deep Networks from Decentralized Data Federate Learning 임진혁 paper
review
O
2021.03.11 Reinforcement learning 01 - MDP, Q-learning Reinforcement Learning 최영제 review O
2021.03.18 [NIPS 2019] FedMD: Heterogenous Federated Learning via Model Distillation Federate Learning, Knowledge Distillation 임진혁 paper
review
O
2021.03.18 Reinforcement learning 02 - DQN, PER, Dueling DQN Reinforcement Learning 최영제 review
blog
X
2021.03.25 [ICML 2017] Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks Meta Learning
Few Shot
임진혁 paper
review
O
2021.03.25 Reinforcement learning 03 - PG, Actor-critic, A2C Reinforcement Learning 최영제 review X
2021.03.31 [ICLR 20201] DOMAIN GENERALIZATION WITH MIXSTYLE Domain Generalization 임진혁 paper
review
O
2021.03.31 Reinforcement learning 04 - A3C, SIL Reinforcement Learning 최영제 review X
2021.04.07 [arXiv 2021] Meta Pseudo Labels Semi-Supervised Learning 임진혁 paper
review
O
2021.04.07 [ICLR 2017] Neural architecture search with reinforcement learning AutoML 최영제 paper
review
X
2021.05.12 [CVPR 2020] Attentive Weights Generation for Few Shot Learning via Information Maximization Few Shot
Attention
임진혁 paper
review
O
2021.05.12 [ICML 2018] Efficient nerual architecture search via parameter sharing AutoML 최영제 paper
review
X
2021.05.25 [ICLR 2015] ADAM : A METHOD FOR STOCHASTIC OPTIMIZATION Optimization 임진혁 paper
review
O
2021.05.25 [arXiv 2020] DIFER, Differentiable automated feature engineering AutoFE 최영제 paper
review
X
2021.06.09 [KDD 2020] USAD, unsupervised anomaly detection on multivariate time series Anomaly Detection 최영제 paper
review
blog
X
2021.06.16 [ICML 2019] Zero-Shot Knowledge Distillation in Deep Networks Knowledge Distillation
Few Shot
임진혁 paper
review
O
2021.06.23 [arXiv 2018] Federated Meta-Learning with Fast Convergence and Efficient Communication Federate Learning
Meta Learning
임진혁 paper
review
O
2021.06.23 [IEEE ICBD 2020] TadGAN, Time series anomaly detection using generative adversarial networks Anomaly Detection 최영제 paper
review
X
2021.06.30 [ICLR 2021] BOIL: TOWARDS REPRESENTATION CHANGE FOR FEW-SHOT LEARNING Meta Learning
Few Shot
임진혁 paper
review
O
2021.06.30 [ICDM 2019] Neural feature search, A nueral architecture for automated feature enigneering AutoFE 최영제 paper
review
X
2021.07.07 [arXiv 2018] Exploration by Random Network Distillation Reinforcement Learning 최영제 paper
review
X
2021.07.16 [NIPS 2019] Domain Generalization via Model-Agnostic Learning of Semantic Features Domain Generalization
Meta Learning
임진혁 paper
review
X
2021.07.21 [PAKDD 2020] Cross data Automatic Feature Engineering via Meta learning and Reinforcement Learning AutoFE 최영제 paper
review
X
2021.08.04 [arXiv 2017] PathNet, Evolution Channels Gradient Descent in Super Neural Networks Transfer Learning 최영제 paper
review
X

ai-study's People

Contributors

eeplearning avatar yjchoi-95 avatar

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.