Basic Core Courses
DIAZ12 Academic Activities (2 credits)
This course aims to expand students' horizons, let students communicate face-to-face through academic seminars and other means, to obtain more up-to-date knowledge of artificial intelligence and etc.
DIAZ01 Artificial Intelligence Principles (3 credits)
Artificial intelligence is the study of how to realize human intelligence by using computer software and hardware to perceive and act upon external environment. Based on the systematical discourse about artificial intelligence, this course aims to introduce the principles of artificial intelligence that is divided into four parts: problem solving, planning, learning and reasoning. Where the three parts as bellow will be taught mainly:
Problems solving approaches for search problem, optimization problem, game problem and constraint problem.
Automatic planning approaches including classical planning, motion planning, and decision theoretic planning.
Knowledge representation methods and their reasoning mechanisms.
And, the learning part will be taught in the course of Machine Learning.
DIAZ02 Machine Learning (3 credits)
Machine learning is seen as a part of artificial intelligence. This course systematically introduces its history and foundational disciplines, and discusses the key points with components to study machine learning, on those bases, detailed teach machine learning for the three perspectives of theoretical “frameworks”, algorithmic “paradigms”, abstract “tasks”. The main contents are as following:
The theoretical frameworks consisting of probabilistic, statistical, geometric, connectionist, symbolic and behaviorist frameworks.
The three major paradigms of supervised learning, unsupervised learning, and reinforcement learning. And in addition transfer learning, meta learning, etc.
The abstract tasks such as classification, clustering, dimensionality reduction, association, decision-making.
DIAZ11 Literature Survey and Thesis Planning (2 credits)
This course aims to let students learn the latest research development in Artificial intelligence, to help students to know the unsolved problems and possible solutions in this field through literature survey, to lead students to choose suitable research directions so as to complete the selection of PhD research topics.
DIAZ13 Dissertation (18 credits)
This course provides students one-to-one guidance of writing an academic thesis from the instructor, with the contents including basic steps of writing thesis, exploring research topics, literature review, research design, conclusions and future works. With the help of the instructor, students can select one topic from applied mathematics, data mining, machine learning and other related research directions and finally complete a professional thesis, confirmed by the instructor.
Elective Courses
DIAE01 Deep Learning (3 credits)
This course provides a comprehensive coverage on theoretical foundations of deep learning. Graduate students will get a systematic and in-depth understanding on the theory of deep learning from this course. The major contents of this course include: mathematical foundations of deep learning, feed-forward neural networks, convolutional neural networks, regularization and optimization of deep models, recurrent neural networks, auto encoders, representational learning, structural probability models, generative models, as well as some typical application scenarios.
DIAE02 Computer Vision (3 credits)
This course describes the theoretical basis and framework in computer vision from both classical part and deep learning-based content. The part of classical computer vision includes hand-crafted feature learning method, the projection transformation from 3D physical world to 2D image plane, etc.; while deep learning-related part will introduce the most cutting-edge technologies and models based on deep neural networks for computer vision. The common computer vision tasks such as image classification, object detection, behavior recognition, etc. are also described. Students are supposed to read related papers and write reports.
DIAE03 Natural Language Processing (3 credits)
The main contents of this course include: 1) Mathematical foundation of natural language processing, n-gram model, generative/discriminative model, word vectors, etc. 2) Linguistic basis of natural language processing, word spelling, word meaning and part of speech, semantic disambiguation, and probability syntactic analysis, etc. 3) Applications of natural language processing, such as text classification and clustering, sentiment analysis, information extraction, machine translation, dialogue system, etc.
DIAE04 Algorithm and Computational Complexity (3 credits)
This course aims to introduce the analysis and the design principles of algorithms Topics includes: analysis of algorithms, divide-and-conquer strategy, dynamic programming, greedy algorithms, graph algorithms, maximum flow problem, probabilistic analysis and randomized algorithms, etc.
DIAE05 Digital Image Processing (3 credits)
This course aims to introduce the basic principles, methods, and applications of digital image processing. The content includes basic methods such as preprocessing of digital images, transformation between spatial and temporal domains and the filtering upon them, data encoding and compression, and feature descriptor design and extraction. At the same time, the traditional statistical pattern recognition and structural pattern recognition methods are introduced, and their applications in different fields are expounded with practical cases. Students are supposed to read related papers and write reports.
DIAE06 Selected Topics in Artificial Intelligence (3 credits)
The course aims to extend the horizon of students, enable students to learn the latest developments, applications and developing trend of related industry in AI field.
