Teaching Experience and Materials
From 2018 to 2022, I taught some Artificial Intelligence knowledge to Chinese graduates, employed programmers, and some researchers. These courses were designed mainly by pragmatical methods and algorithms implemented from scratch. Based on these ways, students could learn related algorithms with a deep understanding and practical application ability. As a result, almost every Chinese top 50 technology company hired my students as their AI engineers or related positions.
Artificial Intelligence and Natural Language Processing
Time: 2018 - 2020
In this course, students will learn the important methods by finishing four pragmatic projects to deal with modern NLP problems. After learning, students will acquire abilities including Dynamic Programming, TextRank, Dependency Parsing, Information Retrieval, RNN(LSTM), CNN, Semantic Classification, Seq2Seq, Machine Translation, and Attention Mechanism.
Course material:
https://github.com/computing-intelligence/jupyters_and_slides
Artificial Intelligence Kernel Capability
Time: 2020 - 2021
Students will learn the critical modern AI methods in this course by finishing eight projects. This course is different from a typical deep learning course and includes heuristic search methods, dynamic programming, classical machine learning methods(Bayesian, Decision Tree, SVM, KMeans, etc.), and modern deep learning methods(CNN, RNN, Embedding, Seq2Seq, Transformer)
Course material link:
https://github.com/computing-intelligence/artificial-intelligence-fundemental-ability
Advanced Python Programming
Time: 2022
Students will have a deeper understanding of python programming. Subjects in this course include dynamic evaluation and its application, advanced oriented function and object programming, parallel and async programming, bottleneck analysis and performance optimization, numerical and scientific computing, and deployment and persistence.
Course material link: