| Learning Course | 이론 (Theory) | 확률론 (Probability theory) → 베이즈 이론 (Bayesian probability) |
| Machine learning | Hypothesis → Loss function → Gradient descent → Overfitting |
| Neural network | Artificial neuron → Perceptron → Multilayer perceptron → (Example) → Feedforward neural network → Activation function (Sigmoid function & Euler's number) → Softmax function (Loss function) → Backpropagation (Gradient descent) → (Example) |
| 딥 러닝 (Deep learning) | 합성곱 신경망 (Convolutional neural network) (CNN) & Region-based Convolutional Network (RCNN, R-CNN) |
| ETC | Tutorials |
| 이론 (Theory) | Basic | 용어 (Terms) |
| 확률론 (Probability theory) | 베이즈 이론 (Bayesian probability), 결정이론 (Decision Theory), 확률 밀도 함수 (Probability Density Function) (PDF), 방사형 기저 함수 (Radial basis function) (RBF), Hyperparameter |
| 신경과학 (Neuroscience)d | 뉴런 (Neuron) |
| 통계학 (Statistics) | 공분산 (Covariance), 통계 분류, 분류행렬 (Confusion matrix), 교차 검증 (Cross-validation), 평균 제곱근 편차 (Root-mean-square deviation) (MESD), Mean squared error |
| 그래프 이론 (Graph theory) | |
| 행렬 (Matrix) | General matrix-matrix multiplication (gemm), Toeplitz matrix, im2col |
| 기타 | Computational learning theory, Empirical risk minimization, Occam learning, PAC learning, Statistical learning, VC theory, 베이즈 네트워크, 마르코프 임의장 (Markov random field), Hidden Markov Model (HMM), Conditional Random Field, 정규 베이즈 분류기 (Normal Bayes Classifier), Energy Based Model, 오컴의 면도날 (Occam's razor), Ground truth |
| 알고리즘 유형 | 지도 학습 (Supervised Learning) | 서포트 벡터 머신 (Support Vector Machine) (SVM), Hidden Markov model, 회귀 분석 (Regression analysis), 신경망 (Neural network), 나이브 베이즈 분류 (Naive Bayes classifier), K-근접이웃 (K-Nearest Neighbor) (K-NN), Decision trees, Ensembles (Bagging, Boosting, Random forest), Relevance vector machine (RVM) |
| 자율 학습 (Unsupervised learning) | 군집화 (Clustering), 독립 성분 분석 (Independent component analysis) |
| 준 지도 학습 (Semi-supervised learning) | Generative models, Low-density separation, Graph-based methods, Heuristic approaches |
| 기타 학습 | 강화 학습 (Reinforcement learning), 심화 학습 |
| 주제별 | 구조적 예측 (Structured prediction) | Graphical models (Bayes net, CRF, HMM) |
| 모수 추정 알고리즘 | 동적 계획법 (Dynamic programming), 기대값 최대화 알고리즘 (EM algorithm) |
| 근사 추론 기법 | 몬테 카를로 방법, 에이다 부스트 (AdaBoost) |
| 접근 방법 | 결정 트리 학습법, 연관 규칙 학습법, 유전 계획법, 귀납 논리 계획법, 클러스터링, 베이지안 네트워크, 강화 학습법, 표현 학습법, 동일성 계측 학습법 |
| 모형화 | 신경망 (Neural network), SVM K-NN, 결정 트리, 유전 알고리즘 (Genetic Algorithm), 유전자 프로그래밍, 가우스 과정 회귀, 선형 분별 분석, 퍼셉트론, 방사 기저 함수 네트워크 |
| Recommender system (추천 시스템) | Collaborative filtering (협업 필터링), Content-based filtering (컨텐츠 기반 필터링), Hybrid recommender systems |
| 데이터 마이닝 (Data mining) | 교차 검증 (Cross-validation) (k-fold), Data set (Training set, Validation set, Test set) |
| 회귀 분석 (Regression analysis) | 선형 회귀 (Linear regression), 로지스틱 회귀 (Logistic Regression), Logit function, Multinomial logistic regression (Softmax Regression) |
| 군집화 (Clustering) | k-means clustering, BIRCH, Hierarchical, Expectation-maximization (EM), DBSCAN, OPTICS, Mean-shift |
| 종류별 | 3D Machine Learning |
| 인공신경망 (Artificial Neural Networks; ANN) | 인공 뉴런 (Artificial neuron) | 퍼셉트론 (Perceptron), Sigmoid neuron |
| 합성함수 (Combination function) & 활성함수 (Activation function) | Sigmoid function, Rectified linear units (ReLU), 1x1 Convolution |
| 손실 함수 (Loss function) or Cost function | Softmax, Sum of squares (Euclidean), Hinge / Margin, Cross entropy, Infogain, Accuracy and Top-k |
| 알고리즘 | 다층 퍼셉트론 (Multilayer perceptron) (MLP), Feed-forward Neural Network (FNN), Long short-term memory (LSTM), Autoencoder, 자기조직화지도 (Self-organizing map) (SOM), Network In Network (NIN), Adaptive neuro fuzzy inference system (ANFIS) |
| 딥 러닝 (Deep learning) | 심층 신경망 (Deep neural network) (DNN), 합성곱 신경망 (Convolutional neural network) (CNN) & Regions with Convolutional Neural Network (RCNN, R-CNN, SSD), 순환 신경망 (Recurrent neural network) (RNN), Gated Recurrent Unit (GRU), 제한 볼츠만 머신 (Restricted Boltzmann Machine) (RBM), 심층 신회 신경망 (Deep Belief Network) (DBN), 심층 Q-네트워크(Deep Q-Networks), Deep hyper network (DHN), Deconvolutional Network, Fully Convolutional Networks for Semantic Segmentation (FCN), Generative Adversarial Networks (GAN), Learning Deconvolution Network for Semantic Segmentation, Multi-Scale Context Aggregation by Dilated Convolutions (Dilated Convolutions), Dynamic Routing Between Capsules (Capsules Network), YOLO, Path Aggregation Network for Instance Segmentation (PANet), Image-to-Image Translation with Conditional Adversarial Networks (pix2pix), CycleGAN, BicycleGAN, SlowFast, Kinetics, AVA, MelGAN, EfficientDet, SinGAN, Panoptic Segmentation, U-Net, MONAI, CenterNet, DeepLab, HRNet, OCRNet, ResNeSt |
| Models | GoogLeNet, LeNet, AlexNet, ReNet, RCNN, SPPnet, Fast R-CNN, Faster R-CNN, VGG, SqueezeNet, PointNet, Mask R-CNN, MaskLab, OSMN (Video Segmentation), ColorNet, EfficientNet |
| Problems | 차원 축소 (Dimensionality reduction) | Curse of dimensionality, Factor analysis, CCA, 독립 성분 분석 (ICA), LDA, 음수 미포함 행렬 분해 (NMF), 주성분 분석 (PCA), t-SNE |
| 과소적합 (Underfitting) & 과적합 (Overfitting) | Early stopping, Model selection, Normalization, Regularization (L1, L2, Dropout), Generalization |
| 초기화 (Initialization) | Xavier Initialization |
| ETC | 편향-분산 딜레마 (Bias-variance dilemma), Vanishing gradient problem, Local minimum problem, Batch Normalization, 표준화 (Standardization), AutoML |
| 최적화 (Optimization) | Hyperparameter, 담금질 모사 (Simulated annealing), Early stopping, Feature scaling, Normal Equation, 경사 하강법 (Gradient descent), Stochastic gradient descent (SGD), 오류역전파 (Backpropagation), Convex optimization, Performance Tuning, im2col, Dense-Sparse-Dense Training for Deep Neural Networks (DSD), Deep Compression, Pruning Neural Networks, Shake-Shake regularization, Accurate Large Minibatch SGD |
| ETC | Libraries | OpenCV, Deeplearning4j (DL4J), Torch, PyTorch, 테아노 (Theano), Caffe, TensorFlow, MMDetection, ConvNetJS, cuDNN, Netscope, Microsoft Azure Machine Learning Studio, OpenPose, DensePose, Keras, tiny-dnn, Detectron, Stanford CoreNLP, Aifiddle, Kubeflow, OpenNMT, alibi-detect, Flashlight (facebook), MediaPipe, Weights and Biases |
| Dataset | MNIST (손 글씨 데이터), ImageNet, CIFAR-10, TinyImages, PASCAL VOC, COCO, AVSS, YouTube-VOS |
| Annotation tools | labelme, cvat, f-BRS, COCO Annotator |
| See also | 인공지능, 자동 로봇, 생체 정보학, 컴퓨터 지능, 컴퓨터 시각, 데이터 마이닝, 패턴 인식, 빅데이터 |
| Unknown keyward | Classification, Anomaly detection, Association rules, Reinforcement learning, Structured prediction, Feature engineering, Feature learning, Online learning, Semi-supervised learning, Unsupervised learning, Learning to rank, Grammar induction, Local outlier factor, Minimum Description Length (MDL), Bayesian MAP, Structural Risk Minimization (SRM), Long Narrow Valley, Word2vec, Autoregressive integrated moving average (ARIMA) |