Building Deep Learning Applications

  NTUT Deep Learning FB Group Playlist   112 Videos

Week Topic Learning Objectives Slides Code Video
Course Requirements
  • Kaggle homework (45%)
  • Midterm (20%)
  • Final project (20%)
  • Quizzes (10%)
  • Attendance & Bonus (5%)
pdf
Text Book François Chollet, Deep Learning with Python, 2nd Edition, Manning, 2021 GitHub
Reference Ian Goodfellow and Yoshua Bengio and Aaron Courville, Deep Learning, MIT Press, 2016 slides
1 Past, Present, and Future of AI
  • Singularity is Coming? Brief History of AI & ChatGPT
pdf
  • Types of neural networks
2 Introduction to Deep Learning
  • What is Machine Learning?
  • Neural Networks, Gradient Descent and Backpropagation
  • State-of-the-arts of deep learning
pdf
3 Applied Math - Linear Algebra
  • Scalar, vector, matrix, tensor
  • Matrix multiplication
  • Dot product and outer product
  • Lp norm
pdf
TensorFlow (Keras)
  • Write TensorFlow code on Google Colab
  • Create a simple Dense Neural Networks
  • Use DNN to solve classification and regression problems
  • Batch, Epoch and Learning rate
pdf IMDB_review
financial_news
house_pricing
4 Applied Math - Probability
  • Mutually exclusive & independence
  • Conditional Probability & Bayes Theorem
  • Naive Bayes classifier
pdf
Machine Learning Basics
  • Five tribes of Machine Learning
  • Classification & Regression
  • Model Capacity, Overfitting & Underfitting
  • Regularization, Cross-validation, Dropout
  • Confusion Matrix, Accuracy, Precision, Recall
pdf classifiers regressors
5 Convolutional Neural Networks (CNNs)
  • Convolution Filters
  • Using pre-trained models
  • AlexNet, Inception, ResNet, Xception
  • NAS & EfficientNet
pdf
SOTA CV models
  • Vision Transformer
  • Swin Transformer
  • ConvNext
6 Advanced Keras API
  • Functional API
  • Multi-input and Multi-output model
  • Depthwise Separable Convolution
pdf
Applied Math - Calculus & Optimization
  • Derivative (Change Rate)
  • Chain Rule
  • Gradient-based Optimization
  • Momentum, AdaGrad, RMSProp & ADAM
pdf
7 Object Detection
  • Region Proposal & RCNN
  • YOLO v1 - v8
  • SSD, FPN, RetinaNet, EfficientDet, CenterNet
pdf Run YOLOv4
Object Tracking
  • OpenCV
  • CSRT
  • DeepSORT, ByteTrack
Image Segmentation
  • Instance, Semantic, and Panoptic Segmentation
  • U-Net, Mask RCNN
  • Segment Anything Model (SAM)
8 NLP & Word Embedding
  • Natural Language Processing
  • N-gram & Skip-gram Model
  • Word2vec
  • GloVe
pdf
9 RNN & LSTM
  • Recurrent Neural Networks
  • LSTM
  • Temporal CNN
pdf
10 Attention & Transformer
  • Attention is All You Need
  • Self-attention
  • Transformer
pdf
Modern NLP Models
  • Bidirectional Encoder Representations from Transformers (BERT)
  • Generative Pre-trained Transformers (GPT)
pdf
Hugging Face NLP Tutorial
11 Generative Deep Learning
  • Generating Text using LSTM
  • Neural Style Transfer
  • Variational Auto Encoder
pdf
Generative Adversarial Networks (GANs)
  • Generative Adversarial Networks
  • Conditional GAN
  • CycleGAN
  • GauGAN, Adversarial Attack
pdf
Stable Diffusion
  • Diffusion is All You Need!
  • Midjourney, DALL-E
  • Stable Diffusion
12 Deep Reinforcement Learning
  • What is Reinforcement Learning?
  • State, Action, Reward and Policy
  • Value-based vs. Policy-based Learning
  • On-policy vs. Off-policy
pdf
13 Deep Learning on Graphs
  • Graphs and Networks
  • Vertices, Edges, Degree
  • Deep Random Walk
  • Graph Convolutions
pdf
Final Project Demo
14 Action Recognition & Pose Estimation
  • Optical Flow
  • Two-stream Model
  • C3D, TSN, and other SOTA Models
pdf
15 Network Pruning and Quantization
  • TensorFlow Lite