1 |
Fundamentals of Deep Learning |
Fundamentals, NN, CNN, RNN |
|
|
|
|
2 |
Model Learning Technique |
Optimizer, GD, SDG, Momentum, RMSProp |
|
|
|
|
|
|
Adagrad |
Adaptive Subgradient Methods for Online Learning and Stochastic Optimization |
|
|
|
|
|
Adam |
Adam: A Method for Stochastic Optimization |
|
|
|
|
|
Schedular |
|
|
|
|
3 |
Model Design Techniques |
Activation Functions, Sigmoid, Tanh, ReLU |
|
|
|
|
|
|
GELU |
Gaussian Error Linear Units (GELUs) |
|
|
|
|
|
Swish |
Searching for Activation Functions |
|
|
|
|
|
Batch Normalization |
Batch Normalization: Accelerating Deep Network Training |
|
|
|
|
|
Layer Normalization |
Layer Normalization |
|
|
|
|
|
Dropout |
Dropout: A Simple Way to Prevent Neural Networks from Overfitting |
|
|
|
4 |
RNN Based Models |
LSTM |
Long Short-Term Memory |
|
|
|
|
|
GRU |
Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation |
|
|
|
|
|
Seq2Seq |
Sequence to Sequence Learning with Neural Networks |
|
|
|
5 |
Transformer |
Attention |
Neural Machine Translation by Jointly Learning to Align and Translate |
|
|
|
|
|
Transformer |
Attention Is All You Need |
|
|
|
6 |
Text Models |
word2vec |
Efficient Estimation of Word Representations in Vector Space |
|
|
|
|
|
BERT |
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding |
|
|
|
|
|
GPT |
Improving Language Understanding by Generative Pre-Training |
|
|
|
7 |
CNN Based Models |
LeNet |
Gradient-Based Learning Applied to Document Recognition |
|
|
|
|
|
AlexNet |
ImageNet Classification with Deep Convolutional Neural Networks |
|
|
|
|
|
ResNet |
Deep Residual Learning for Image Recognition |
|
|
|
|
|
Inception |
Going Deeper with Convolutions |
|
|
|
8 |
Image Detection Models |
R-CNN |
Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation |
|
|
|
|
|
Fast R-CNN |
Fast R-CNN |
|
|
|
|
|
Faster R-CNN |
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks |
|
|
|
|
|
YOLO |
You Only Look Once: Unified, Real-Time Object Detection |
|
|
|
9 |
Other Learning Methods |
Contrastive Learning |
A Simple Framework for Contrastive Learning of Visual Representations |
|
|
|
|
|
Few-Shot Learning |
Matching Networks for One Shot Learning |
|
|
|
|
|
Knowledge Distillation |
Distilling the Knowledge in a Neural Network |
|
|
|
10 |
Generative Models |
VAE |
Auto-Encoding Variational Bayes |
|
|
|
|
|
GAN |
Generative Adversarial Networks |
|
|
|
|
|
Diffusion |
Denoising Diffusion Probabilistic Models |
|
|
|
11 |
Graph Based Models |
GNN |
The Graph Neural Network |
|
|
|
|
|
GCN |
Semi-Supervised Classification with Graph Convolutional Networks |
|
|
|
|
|
GAT |
Graph Attention Networks |
|
|
|
12 |
Fundamental of Reinforcement Learning |
Q-Learning |
|
|
|
|
|
|
SARSA |
|
|
|
|
|
|
DQN |
Playing Atari with Deep Reinforcement Learning |
|
|
|
|
|
PG |
Policy Gradient Methods for Reinforcement Learning with Function Approximation |
|
|
|