Paper Review
Paper Review Seminar (2024)
Mamba: Linear-Time Sequence Modeling with Selective State Spaces (Kyuchul Lee)
Youtube: https://youtu.be/fURRobLWkqcLlm in a flash: Efficient large language model inference with limited memory (Kyumin Khang)
Youtube: https://youtu.be/9AZ067J1O_o
Paper Review Seminar (2023)
The Curse of Recursion: Training on Generated Data Makes Models Forget (Suyeong Lim)
Youtube: https://youtu.be/LwijXgZ9MxgDistribution Aligning Refinery of Psuedo-label for Imbalanced Semi-supervised Learning (Sangjae Lee)
Youtube: https://youtu.be/_fTH5iFxZ6cZero-shot Text-to-image Generation (Myunghyun Lee)
Youtube: https://youtu.be/rRwwIn07UBMTapNet: Multivariate Time Series Classification with Attentional Prototypical Network (Hyemin Han)
Youtube: https://youtu.be/RT00AllOhNELanguage Models are Few Shot Learners and GPT Practical Tips (Kyu Min Khang)
Youtube: https://youtu.be/UMQ227ANobcAnomaly Transformer: Time Series Anomaly Detection with Association Discrepancy (Kyuchul Lee)
Youtube: https://youtu.be/1ggV-0Y0rkEN-BEATS: Neural basis expansion analysis for interpretable time series forecasting (Cheyun Yeo)
Youtube: https://youtu.be/OVKSrGuc9v8An Image is worth 16x16 words: transformers for image recognition at scale (Hyung Won Kim)
Youtube: https://youtu.be/HreXqenSM9gA Comprehensive Survey of Recent Trends in Data Augmentation (Kyu Min Khang)
Youtube: https://youtu.be/Im1bHL0oyDYMemorizing Normality to Detect Anomaly (Kyuchul Lee)
Youtube: https://youtu.be/v8ES9azY7lAUsad: Unsupervised anomaly detection on multivariate time series (Chaeyun Yeo)
Youtube: https://youtu.be/rkPwOWYeqhkA Simple Framework for Contrastive Learning of Visual Representations (Hyung Won Kim)
Youtube: https://youtu.be/BHmJEvkN8ZUAuto-encoding variational bayes (Kyuchul Lee)
Youtube: https://youtu.be/inqCpKKipr8Time Series Forecasting Using Various Deep Learning Models (Chaeyun Yeo)
Youtube: https://youtu.be/qYwxTZLQFsoContraCluster: Learning to Classify without Labels by Contrastive Self-Supervision and Prototype-Based Semi-Supervision (Hyung Won Kim)
Youtube: https://youtu.be/QFCkwCg8Z98
Paper Review Seminar (2022)
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding (Jae Young Kim)
Youtube: https://youtu.be/2AvoJPhrOQYEfficient NetV2: Smaller Models and Faster Training (Chaeyun Yeo)
Youtube: https://youtu.be/T10Fck86U0IEfficient Net: Rethinking Model Scaling for Convolutional Neural Networks (Chaeyun Yeo)
Youtube: https://youtu.be/3J0AHnLK82cDETR: End-to-End Object Detection with Transformer (Doo Jin Lee)
Youtube: https://youtu.be/U7FlIvorkR0CNC Machine AI Practice (Shin Hoon Kang)
Youtube: https://youtu.be/JtXza8ooX3sA Machine Learning Algorithm to Estimate the Probability of a True Scaphoid Fracture after Wrist Trauma (Hyung Won Kim)
Youtube: https://youtu.be/hAUYdjbTajoDeep High Resolution Representation Learning for Human Pose Estimation (Jae Young Kim)
Youtube: https://youtu.be/jfTYYsOa3nEAn Image is Worth 16 x 16 Words: Transformers for Image Recognition at Scale (Jae Young Kim)
Youtube: https://youtu.be/tlz8NmbOQ80Deep Learning Model Study for Bitcoin Price Prediction (Presenter: Hyung Won Kim)
Youtube: https://youtu.be/uSUwES-d4FoImageNet Classifciation with Deep Convolutional Neural Network (Presenter: Doo Jin Lee)
Youtube: https://youtu.be/olqWSIDCsDYData Analysis for CNC Machine Operation (2) (Presenter: Shin Hoon Kang)
Youtube: https://youtu.be/3auc8GYUP6YYou Only Look Once: Unified, Real-time Object Detection (Presenter: Doo Jin Lee)
Youtube: https://youtu.be/OZtEL9dydLMAttention is All You Need (Presenter: Jae Young Kim)
Youtube: https://youtu.be/fm70Me6IxrMMulti-classification Deep CNN Model for Diagnosing COVID (Presenter: Hyung Won Kim)
Youtube: https://youtu.be/KE15QUkKVTgData Analysis for CNC Machine Operation (Presenter: Shin Hoon Kang)
Youtube: https://youtu.be/WKzQAo7wB18
Book Review
Generative Deep Learning (2023)
Chapter 1. Introduction (Kyu Min Khang, Suyeong Lim)
Youtube: https://youtu.be/HxDTMn6HJPwChapter 2. Deep Learning (Kyu Min Khang, Eunkyeong Lee)
Youtube: https://youtu.be/eGJ6e5iG5zcChapter 3. Variational Autoencoder (Kyuchul Lee, Myunghyun Lee)
Youtube: https://youtu.be/TJbY0-d9p5gChapter 4. Generative Adversarial Network (Cheyun Yeo, Hyemin Han)
Youtube: https://youtu.be/WTyhAgc4LEsChapter 5. Autoregressive Models (Sangjae Lee, Myunghyun Lee)
Youtube: https://youtu.be/j1sdfIgjDLQChapter 6. Normalizing Flow (Kyu Min Khang, Hongjin Kim)
Youtube: https://youtu.be/94WlFyf3DFgChapter 7. Energy based Models (Ji Hyun Kim, Myunghyun Lee)
Youtube: https://youtu.be/lET6yQzIp-gChapter 8. Diffusion Model (Kyuchul Lee, Eunkyeong Lee)
Youtube: https://youtu.be/QgiY0HTA2ckChapter 9. Transformers (Cheyun Yeo, Suyeong Lim)
Youtube: https://youtu.be/VZRb5gjjHSUChapter 10. Advanced GAN (Minjae Cha, Sangjae Lee)
Youtube: https://youtu.be/KhALo8gng2AChapter 11. Music Generation (Hongjin Kim, Kyu Min Khang)
Youtube: https://youtu.be/hTf9xo2gK7MChapter 12. World Models (Cheyun Yeo, Ji Hyun Kim)
Youtube: https://youtu.be/ssVTxiaiyaQChapter 13. Multimodal Models (Sangjae Lee, Kyuchul Lee)
Youtube: https://youtu.be/A03XUGOywC8
Deep Learning with Pytorch (2022)
Chapter 1. Introducing Deep Learning and Pytorch Library (Presenter: Jae Young Kim)
Youtube: https://youtu.be/V6It47iMu_gChapter 2. Pretrained Networks (Presenter: Hyung Won Kim)
Youtube: https://youtu.be/sdeAc64GFeEChapter 3. It Starts with a Tensor (Presenter: Shin Hoon Kang)
Youtube: https://youtu.be/mIl94_1wolsChapter 4. Real-world Data Representation using Tensor (Presenter: Do Young Lee)
Youtube: https://youtu.be/r51VOwHXYGkChapter 5. The Mechanics of Learning (Presenter: Doo Jin Lee)
Youtube: https://youtu.be/QlKulpTmdIIChapter 6. Using a Neural Network to Fit the Data (Presenter: Jae Young Kim)
Youtube: https://youtu.be/RNOopxKiXZcChapter 7. Telling Birds from Airplanes (Presenter: Hyung Won Kim)
Youtube: https://youtu.be/KR10ZLKnohgChapter 8. Using Convolutions to Generalize (Presenter: Shin Hoon Kang)
Youtube: https://youtu.be/1vGOoO-9F50Chapter 9. Using Pytorch to Fight Cancers (Presenter: Doo Jin Lee)
Yourtube: https://youtu.be/YI3XHz7XG4kChapter 10. Combining Data Sources into an Unified Dataset (Presenter: Jae Young Kim)
Yourtube: https://youtu.be/cMda96QT3aMChapter 11. Training a Classification Model to Detect Suspected Tumors (Presenter: Hyung Won Kim)
Youtube: https://youtu.be/saawSCwmml8Chapter 12. Improving Training with Metrics and Augmentation (Presenter: Shin Hoon Kang)
Youtube: https://youtu.be/vxeJgY2xuHYChapter 13. Using Segmentation to Find Suspected Nodules (Presenter: Doo Jin Lee)
Youtube: https://youtu.be/Ceo2HeqbV5wChapter 14. End-to-End Nodule Analysis, and Where to Go Next (Presenter: Jae Young Kim)
Youtube: https://youtu.be/X8pwqyS0Vxs
Basic Programming Skills
Programming Tools for Machine Learning Research
Docker and SSH (Sangjae Lee, Minjae Cha)
Youtube: https://youtu.be/fQyYwy43TrQVSCode and WSL (Kyumin Khang, Sangjae Lee)
Youtube: https://youtu.be/-tK17eGbsXs
Resources
Deep Learning and Machine Learning
(Book) Deep Learning, Ian Goodfellow, Yoshua Bengio, and Aaron Courville.
(Book) The Elements of Statistical Learning, Trevor Hastie, Robert Tibshirani, and Jerome Friedman.
(Book) Deep Learning with Python, François Chollet.
(Book) Deep Learning with Pytorch, Eli Stevens, Luca Antiga, and Thomas Viehmann.
(Book) Hands on Machine Learning, Aurélien Géron.
(Book) Interpretable Machine Learning, Christoph Molnar.
(Book) Natural Language Processing with Transformers, Lewis Tunstall, Leandro von Werra, and Thomas Wolf.
(Book) Statistical Rethinking: A Bayesian Course with Examples in R and STAN, Richard McElreath.
(Library) Ray Data, Train, Tune.
(Youtube) Convolutional Neural Networks for Visual Recognition, Stanford CS231n.
(Youtube) Natural Language Processing with Deep Learning, Stanford CS224n.
(Youtube) Statistical Rethinking, Richard McElreath.
Physics Informed Machine Learning
(Youtube) Physics Informed Machine Learning, Steve Brunton
(Youtube) Engineering Math: Differential Equations and Dynamical Systems, Steve Brunton
(Youtube) PySINDY Tutorial, Alan Kaptanoglu
(Book) Kalman-and-Bayesian-Filters-in-Python
Reinforcement Learning
(Book) Reinforcement Learning, Richard Sutton and Andrew Barto.
(Book) Grokking Deep Reinforcement Learning, Miguel Morales.
(Book) Deep Reinforcement Learning Hands-on, Maxim Lapan.
(Youtube) Reinforcement Learning, David Silver.
(Library) Ray RLlib: Industry-Grade Reinforcement Learning.
(Library) TorchRL: Reinforcement learning library with pytorch.
Convex Optimization
(Book) Convex Optimization, Stephen Boyd and Lieven Vandenberghe.
(Youtube) Convex Optimization, Stanford.
(Library) CVX (Matlab), CVXPY (Python).
Path Planning for Mobile Robot and Autonomous Driving
(Youtube) Mobile Robot Systems Course, University of Cambridge.
(Library) Vectorized Multi Agent Simulator (VMAS).
(Library) Multi-Agent path planning in Python.
(Library) Matlab Navigation Toolbox, Automated Driving Toolbox
(Library) CARLA: Open-source simulator for autonomous driving research.
(Book) Elements of Robotics
Datasets
KAMP-AI Manufacturing Industry Dataset (Manufacturing Dataset)
AIHub Data Repository (General AI real-world Problem)
UCI Machine Learning Data Repository (General Benchmark)
WM-811K Wafer Map Pattern Dataset (Semiconductor Wafer Bin Map)
Berkeley Deep Drive Dataset (Autonomous Driving)
DAGM 2007 Competition Dataset (Anomaly Detection)
The mvtec anomaly detection dataset (Anomaly Detection for Industry)
Programming
(Youtube) 생활코딩 Docker 입구 수업.
(Youtube) 생활코딩 SSH 사용법
(Youtube) 생활코딩 Visual Studio Code 기본 사용법