본 포스팅은 고려대학교 산업경영공학부 Data Science & Business Analytics 연구실의 강필성 교수님의 자료를 정리한 포스팅입니다.

Contents of Posting

• Contents of Posting
• Paper Reading Roadmap
  • ML Basics
  • Data Mining
    • General
    • Patter Mining
    • Clustering
  • Artificial Intelligence
    • General
    • Reinforcement Learning
    • Transfer Learning
  • Supervised Learning
    • Kernel Machines
    • Ensemble
  • Semi-supervvised Learning
  • Unsupervised Learning
  • Neural Network
    • General
    • Structure
    • Learning Strategies
  • NLP
    • General
    • Topic Modeling
    • Repersentation Learning
    • Classification
    • Summarization
    • Machine Translation
    • Question Answering
  • Vision
    • Classification
    • Object Detection
    • Localization & Segmentation

Paper Reading Roadmap

ML Basics

• The matrix calculus you need for deep learning
• Statistical Modeling: The Two Cultures
• Machine learning: Trends, perspectives, and prospects
• An introduction to ROC analysis
• Learning from imbalanced data
• Variational inference: A review for statisticians
• The expectation-maximization algorithm
• Dimension Reduction: A Guided Tour

Data Mining

General

• Interestingness Measures for Data Mining: A Survey
• The PageRank citation ranking: Bringing order to the web
• Process Mining Manifesto
• An Introduction to Variable and Feature Selection

Patter Mining

• Fast Algorithm for Mining Association Rules
• A survey of sequential pattern mining
• A Survey of Parallel Sequential Pattern Mining

Clustering

• A density-based algorithm for discovering clusters in large spatial databases with noise
• Data Clustering: A Review
• Techniques of Cluster Algorithms in Data Mining
• Survey of Clustering Data Mining Techniques
• On Clustering Validation Techniques
• clValid: An R Package for Cluster Validation

Artificial Intelligence

General

• Learning Deep Architectures for AI
• Representation learning: A review and new perspectives
• Generative Adversarial Networks
• From evolutionary computation to the evolution of things
• Probabilistic machine learning and artificial intelligence
• AutoML: A Survey of the State-of-the-Art

Reinforcement Learning

• Human-level control through deep reinforcement
• Mastering the game of Go with deep neural networks and tree search
• An Introduction to Deep Reinforcement Learning
• World Models

Transfer Learning

• Zero-shot learning through cross-modal transfer
• Lifelong Learning with Dynamically Expandable Networks

Supervised Learning

Kernel Machines

• An Introduction to Kernel-based Learning Algorithms
• A Tutorial on Support Vector Machine for Pattern Recognition
• A Tutorial on Support Vector Regression
• A Tutorial on nu-Support Vector Machines

Ensemble

• Bagging Predictors
• Random Forests
• A short introduction to boosting
• Greedy Function Approximation: A Gradient Boosting Machine
• Gradient Boosting Machine, A Tutorial
• XGBoost: A Scalable Tree Boosting System
• LightGBM: A Highly Efficient Gradient Boosting Decision Tree
• CatBoost : unbiased boosting with categorical features

Semi-supervvised Learning

• Combining Labeled and Unlabeled Data with Co-Training
• Semi-supervised Learning with Deep Generative Models
• Semi-Supervised Classification with Graph Convolutional Networks
• MixMatch: A Holistic Approach to Semi-Supervised Learning
• ReMixMatch: Semi-Supervised Learning with Distribution Alignment and Augmentation Anchoring
• FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence

Unsupervised Learning

• Anomaly Detection: A Survey
• Deep Learning for Anomaly Detection: A Survey
• A Review of Novelty Detection
• LOF: Identifying Density-Based Local Outliers
• Support Vector Data Description
• Isolation Forest
• Isolation-based Anomaly Detection
• DeepLog: Anomaly Detection and Diagnosis from System Logs through Deep Learning

Neural Network

General

• Deep learning

Structure

• Long Short-Term Memory
• LSTM: A Search Space Odyssey
• Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling Sequence to sequence learning with neural networks
• Memory Networks
• End-To-End Memory Networks
• WaveNet: A Generative Model for Raw Audio
• An Introduction to Variational Autoencoders
• A Comprehensive Survey on Graph Neural Networks

Learning Strategies

• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Dropout: A Simple Way to Prevent Neural Networks from Overtting
• ADAM: A Method for Stochastic Optimization
• An overview of gradient descent optimization algorithms
• Layer normalization
• Group normalization

NLP

General

• Natural Language Processing (Almost) from Scratch
• Advances in natural language processing
• Recent trends in deep learning based natural language processing

Topic Modeling

• An introduction to latent semantic analysis
• Probabilistic latent semantic analysis
• Probabilistic topic models
• Latent Dirichlet Allocation

Repersentation Learning

• A Neural Probabilistic Language Model
• Distributed representations of words and phrases and their compositionality
• Efficient Estimation of Word Representations in Vector Space
• Glove: Global vectors for word representation
• Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation
• Enriching word vectors with subword information
• Bert: Pre-training of deep bidirectional transformers for language understanding
• Deep contextualized word representations
• Improving language understanding by generative pre-training
• Language models are unsupervised multitask learners
• Language Models are Few-Shot Learners

Classification

• Convolutional neural networks for sentence classification
• Deep learning for sentiment analysis: A survey

Summarization

• TextRank: Bringing Order into Texts
• A Neural Attention Model for Abstractive Sentence Summarization

Machine Translation

• On the Properties of Neural Machine Translation: Encoder-Decoder Approaches
• Effective Approaches to Attention-based Neural Machine Translation
• Neural Machine Translation by Jointly Learning to Aligh and Translate
• Google’s Neural Machine Translation System: Bridging the Gap between Human and Machine Translation
• Attention is all you need

Question Answering

• VQA: Visual Question Answering
• Ask Me Anything: Dynamic Memory Networks for Natural Language Processing
• Squad: 100,000+ questions for machine comprehension of text
• Know what you don’t know: Unanswerable questions for SQuAD

Vision

Classification

• Imagenet classification with deep convolutional neural networks
• Visualizing and understanding convolutional networks
• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Going deeper with convolutions
• Deep residual learning for image recognition
• Densely Connected Convolutional Networks

Object Detection

• Overfeat: Integrated recognition, localization and detection using convolutional networks
• Rich feature hierarchies for accurate object detection and semantic segmentation
• Fast R-CNN
• Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
• You Only Look Once: Unified, Real-Time Object Detection
• YOLO9000: Better, Faster, Stronger
• YOLOv3: An Incremental Improvement
• YOLOv4: Optimal Speed and Accuracy of Object Detection

Localization & Segmentation

• U-Net: Convolutional Networks for Biomedical Image Segmentation
• Learning deep features for discriminative localization
• Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization