Notes

These notes were recorded various important points for personal review. It contains brief descriptions.

Linear Algbera

1. Miscellaneous: Some knowledge points for quick review.

Machine Learning

1. Miscellaneous: Basic knowledge points for quick review.

2. Probabilistic stuffs: Some probabilistic knowledge points.

3. Metric learning: Some popular metric learning methods.

4. Attention neural network: Some concepts and principles about attention neural network for quick review.

5. Incremental learning: Some knowledge and paper review about incremental learning (or solving catastrophic forgetting in deep learning).

6. Reinforcement learning quick points: Some important knowledge points about RL.

7. The review of RL book: My notes about the book “Reinforcement Learning: An Introducation” by Richard S. Sutton and Andrew G. Barto, Nov 5, 2017.

8. Semantic video segmentation: The notes about a little semantic video segmentation.

9. Test: The notes for final test (XMU). It briefly contains several important ML knowledge points like searching, probabilistic graph model, neural network, markov decision process.

10. Expectation maximization: A brief and intuitive explanation about EM algorithm.

SLAM

1. Optimization: Nonlinear optimization methods.

2. Camera model: The introducation about camera model, fundamental, essential and homography matrix.

3. Pose graph: The optimization on pose graph and the G2O usage.

4. Bundle adjustment: The optimization for bundle adjustment.

5. Graph simiplification: Simplify the dense pose graph.

6. Point cloud registration: Introduce the optimization problem in solving least square. It includes a general introduction about Non-linear optimization (Gauss Newton and Levenberg-Marquardt methods).

7. Lie group and Lie algebra: An intuitive introduction about Lie algebra.

Algorithms

1. Dynamic programming: An introduction about the dynamic programming algorithm.

2. AVL Tree: The self-balancing binary search tree.

3. Graph algorithm: An introduction about graph-related algorithms.

4. Sorting and searching: An introduction about sorting and searching algorithms.

5. String and array: An introduction about string and array related algorithms.

Data Structure

1. Concepts: An introduction about the concepts of data structure.

2. Structures: Various data structure (e.g. stack, graph).

English

1. Sentences: The sentences for daily expression.

2. Words: The words.

Interview

1. Overview: The overview of interview questions and algorithms.

Paper

1. Object detection: Academic paper about object detection.

2. Human pose estimation: Academic paper about human pose estimation.

3. Few-shot learning: Academic paper about few-shot learning.

4. Continual learning: Academic paper about continual learning.