| Week |
Course Content |
| Week 1 |
Course Logits
Regression ( I II )
|
| Week 2 |
Multi-Layer Perceptron
Non-Linearity of MLP
Implementation: Retrieving Data
Forward Propagation and Cost (*)
Back Propagation (*) |
| Week 3 |
Cost and Objective
Against Overfitting: Regularization and Perturbations
Numerical Stability and Initialization
Implementation: MLP |
| Week 4 |
TensorFlow: Brief Intro
Building Computation Graph: Node as Tensorflow Layer
Information Storage and Transmission among Tensorflow Layers |
| Week 5 |
Sequential Model
Activation Function
Parameter Assessment
From Python function to Tensorflow Graph |
| Week 6 |
Storing Model and Visualization
Gradient Tape ( I II )
Native Training Loop in Tensorflow
Training and Inference Using tf.keras.Model |
| Week 7 |
Model.Compile()
Model.Fit()
Customize Fit()
Customize Callbacks |
| Week 8 |
Sequencing and Preprocessing in Tensorflow
Dataset in Tensorflow
TFRecord data format |
| Week 9 |
The Representation of Data and Signal
Independent Component Analysis
MAP Assumption
Morphology Description |
| Week 10 |
Mutual Coherence
Dictionary Learning
Convolutional Dictionary Learning
ADMM for CDL |
| Week 11 |
Joint ADMM with Convergence Property
Adaptive ADMM for CDL
Fundamental Elements of Convolution Net |
| Week 12 |
Convolution Layer in TensorFlow
Family of LeNet
Implementation: LeNet, AlexNet, VGG
Batch Normalization |
| Week 13 |
ResNet
DenseNet
Introduction to Recurrent Neural Net
Sequential Data
Dealing Numeric Sequential Data in TensorFlow |
| Week 14 |
Attention Mechanism
Optimization Methods |
| Week 15 |
Generative Adversarial Network
Reinforcement LearningApplications
|
| Week 16 |
Final project presentation |
| Week 17 |
自主跨域學習 |
| Week 18 |
自主跨域學習 |