Overview

순서대로 읽을 필요는 없습니다!

---

Part 1

Part 1은 범용적인 개념들에 대해 다룹니다.

• 000 Machine Learning (ML)
  • 0000 ML Terms & Concepts
  • 0001 Rule-based ML
  • 0002 Learning-based ML
  • 0003 Learning Methods
• 001 Tensorflow (TF)
  • 0010 TF Basic
  • 0011 TF Advanced
  • 0012 TF Master
• 002 Deep Learning (DL) Part 1
  • 0020 DL Terms & Concepts
  • 0021 Gradient Descent & Momentum
  • 0022 Back Propagation
  • 0023 Loss & Metric
  • 0024 Activation Function
  • 0025 Initialization
• 003 Image Processing
  • 0030 Preprocessing & Augmentation
  • 0031 Popular Image Dataset
• 004 Deep Learning (DL) Part 2
  • 0040 Multi-layer Perceptron (MLP)
  • 0041 Norm Penalty
  • 0042 Dropout
  • 0043 Convolutional Neural Network (CNN)
  • 0044 Adaptive Learning Rate
  • 0045 Batch Normalization (BN)
  • 0046 Recurrent Neural Network (RNN)
• 005 Sequence Processing
  • 0050 Preprocessing & Masking
  • 0051 Popular Sequence Dataset
• 006 Deep Learning (DL) Part 3
  • 0060 Autoencoder (AE)
  • 0061 Language Model (LM)
  • 0062 Word Embedding
  • 0063 Residual Connection
  • 0064 Sequence-to-Sequence (Seq2Seq)
  • 0065 Encoder-Decoder Model
• 007 Pretrained Model
  • 0070 Alexnet
  • 0071 VGGnet
  • 0072 Inception
  • 0073 Resnet
• 008 Speech Processing
  • 0080 Speech Preprocessing
  • 0081 Popular Speech Dataset

---

Part 2

Part 2는 키워드를 중심으로 관련된 내용을 논문을 통해 다룹니다.

• 110 Attention Model
  • 1100 Learning to Align
• 111 Generative Adversarial Network (GAN)
  • 1110 GAN & DCGAN
  • 1111 Stabilizing Techniques
• 112 Transfer Learning
  • 1120 Adopting Pretrained Model
  • 1121 Knowledge Distillation
  • 1122 Fitnet
  • 1123 Net2Net
• 113 Various Network
  • 1130 Maxout network
  • 1131 Network in Network
  • 1132 Highway Network
• 114 Various Normalization
  • 1140 Layer Normalization
  • 1141 Weight Normalization
  • 1142 Cosine Normalization
• 115 Restricted Boltzmann Machine (RBM)
  • 1150 Energy-based Model
  • 1151 Contrastive Divergence
  • 1152 RBM Pretraining
  • 1153 Deep Belief Network (DBN)
• 116 Denoising Autoencoder (DAE)
• 117 Variational Autoencoder (VAE)
• 118 Connectionist Temporal Classification (CTC)
• 119 Efficient Softmax
• 120 Large Image Processing
  • 1200 Sliding Window
  • 1201 Image Pyramid
  • 1202 Non-maximum Suppression (NMS)
  • 1203 Overfeat
• 121 Ladder Network
• 122 CNN Visualization
  • 1220 DeCaf
• 123 Image Segmentation
  • 1230 R-CNN
  • 1231 Fast R-CNN
  • 1232 Faster R-CNN
  • 1233 You Only Look Once (YOLO)
• 124 Pruning & Compression
  • 1240 SqueezeNet
  • 1241 Dense-Sparse-Dense (DSD
• 125 Fixed Point Network
  • 1250 Retraining Technique
  • 1251 BinaryConnect
  • 1252 BinaryNet
  • 1253 Quantized Neural Networks
• 126 Neural Machine Translation (NMT)
• 127 Memory Model
• 128 Autoregressive Generative Model
• 129 Curriculum Learning
• 130 Distributed Training
• 131 Question & Answer
• 132 Recommendation System
• 133 Density Estimation
• 134 Domain Adaptation
• 135 Super Resolution
• 136 Beam Search & Decoding
• 137 Data Visualization
  • 1370 Principal Component Analysis (PCA)
  • 1371 Linear Discriminant Analysis (LDA)
  • 1372 T-SNE
• 138 One-shot Learning
• 139 Energy-based Training
• 140 Style Transfer
  • 1400 Neural Artistic Style
• 141 Hardware Optimization
• 142 RNN Training Techniques
  • 1420 Zoneout
  • 1421 Scheduled Sampling
  • 1422 Teacher & Professor Forcing
• 143 Time-varying RNN
  • 1430 Hierarchical Multiscale RNN
• 144 Why Deep Learning Works Well
• 145 Speech Generation
  • 1450 WaveNet
  • 1451 Deep Voice
  • 1452 SampleRNN
• 146 Speech Recognition
  • 1460 Deep Speech
• 147 Complex CNN
  • 1470 All Convolution Net
  • 1471 Densly Connected CNN
  • 1472 U-Net
• 148 Stochastic Behaviors
  • 1480 Stochastic Pooling
  • 1481 Stochastic Backpropagation
  • 1482 Stochastic Depth
• 149 Adversarial Attack
• 150 Image Captioning
• 151 Sentence & Document Compression
• 152 Efficient CNN
  • 1520 Separable Filter
• 153 Efficient RNN
  • 1530 Quasi-RNN
• 154 Neural Turing Machine (NTM)
• 155 Training Without Gradient Descent