| L0: Introduction |
overview of the course, logistics, in-class exam |
|
| L1: Linear Algebra (I) |
vector, matrix |
|
| L2: Linear Algebra (II) |
linear space, eigendecompostion |
|
| L3: Linear Algebra (III) |
singular value decomposition, matrix calculus |
|
| L4: Numerical Optimization |
linear regression, principal component analysis |
|
| Discussion 1 |
Python, Numpy, Matplotlib |
|
| L5: Lighting and Shading |
light transport, image formation |
|
| L6: Filters |
linear filters, median filter |
|
| L7: Neural Network |
neural network, image classification |
|
| L8: Statistical and Optimization Perspectives of Deep Learning |
SGD, universal approximation theorem, bias-variance tradeoff, ovefitting and underfitting |
|
| L9: Convolutional Neural Network |
concepts in CNN, hyperparameter tuning, momentum, data augmentation |
|
| L10: Object Recognition |
object detection, segmentation |
|
| L11: Interpreting Neural Networks |
visualizing features, adversarial examples, neural style transfer |
|
| L12: 3D Deep Learning |
learning for point cloud, volumetric CNN, sparseconvnet, point net |
|
| L13: Camera Model |
review of neural networks, pinhole camera model |
|
| L14: Epipolar Geometry |
epipolar line, epipole |
|
| L15: Fundamental Matrix |
essential matrix, fundamental matrix |
|
| L16: Stereo Reconstruction |
estimate fundamental matrix, multi-view 3D reconstruction |
|
| L17: Optical Flow |
optical flow concept, estimation |
|
| L18: Lucas-Kanade Algorithm |
Lucas-Kanade Algorithm, Harris Corner |
|
| L19: Final Review |
|
|