1
课程详述
COURSE SPECIFICATION
以下课程信息可能根据实际授课需要或在课程检讨之后产生变动。如对课程有任何疑问,请联
系授课教师。
The course information as follows may be subject to change, either during the session because of unforeseen
circumstances, or following review of the course at the end of the session. Queries about the course should be
directed to the course instructor.
1.
课程名称 Course Title
机器学习与神经科学 Machine Learning and Neuroscience
2.
授课院系
Originating Department
生物医学工程系 Department of Biomedical Engineering
3.
课程编号
Course Code
BMEB212
4.
课程学分 Credit Value
3
5.
课程类别
Course Type
专业选修课 Major Elective Courses
6.
授课学期
Semester
春季 Spring
7.
授课语言
Teaching Language
英文 English
8.
他授课教师)
Instructor(s), Affiliation&
Contact
For team teaching, please list
all instructors
刘泉影,生物医学工程系,助理教授
liuqy@sustech.edu.cn
Quanying Liu, Biomedical Engineering, Assistant Professor
9.
/助教系、
方式
Tutor/TA(s), Contact
梁智超
11930756@mail.sustech.edu.cn
Zhichao Liang, Biomedical Engineering
10.
选课人数限额(不填)
Maximum Enrolment
Optional
2
授课方式
Delivery Method
习题/辅导/讨论
Tutorials
实验/实习
Lab/Practical
其它(请具体注明)
OtherPlease specify
总学时
Total
11.
学时数
Credit Hours
48
12.
先修课程、其它学习要求
Pre-requisites or Other
Academic Requirements
高等数学 A(下)(MA102B)、线性代数 AMA107A
13.
后续课程、其它学习规划
Courses for which this course
is a pre-requisite
14.
其它要求修读本课程的学系
Cross-listing Dept.
教学大纲及教学日历 SYLLABUS
15.
教学目标 Course Objectives
本课程的教学目标是:让学生对大脑的工作机制有基础的认识,例如视觉系统、运动系统。掌握常用的数学模型和机器学
习方法,包括一些经典的参数估计方法,如最大似然估计法,贝叶斯参数估计方法,以及不同模型之间的比较方法,还包
括更多神经网络模型。了解神经影像技术及其脑科学中的应用,以小组的形式完成一次课程课题研究。
The goal of this course is as following: understanding the neural basis of how brain works, such as the visual system and
motor system; learning some common mathematical models and machine learning methods, including basic parameter
estimation techniques, maximum likelihood parameter estimation and Bayesian parameter estimation, model
comparisons and the neural networks. During the course, students will form course project groups to work on some
scientific questions in neuroscience or psychology field, by using basic neuroimaging techniques and computational
models learned in the course.
16.
预达学习成果 Learning Outcomes
通过学习,本课程预达下列学习成果:
1. 对大脑的工作机制有基础的认识
2. 掌握常用的数学模型和机器学习方法
3. 了解基础的神经影像技术,及其在探索认知和行为中的应用
4. 以小组的形式,研究一个具体的认知和行为的科学问题,阅读相关研究文献,提出探索该问题的相应实验设计、
建模方法、神经信号处理方法,并提出其研究结果可能的假说,写一篇课程项目报告。
5. 展示小组研究成果,完成课程小组汇报。
After one semester of course study, we plan to achieve the following goal:
1. Understanding the neural basis and mechanisms of brain.
2. Knowing some common mathematical models and machine learning methods.
3. Knowing some neuroimaging techniques, and their application in investigating the cognition and behaviour.
4. Forming course project groups, in order to work on specific scientific questions on cognition and behaviour,
including searching/reading relevant literature, designing some experiments, presenting some computational
models and data processing pipeline, and proposing some possible hypotheses, and finally writing a course
report.
5. Presenting the research results in a project presentation.
17.
课程内容及教学日历 (如授课语言以英文为主,则课程内容介绍可以用英文;如团队教学或模块教学,教学日历须注明
主讲人)
Course Contents (in Parts/Chapters/Sections/Weeks. Please notify name of instructor for course section(s), if
this is a team teaching or module course.)
3
Section 1 神经科学、认知行为与计算模型简介(3 学时)
从神经科学、人的认知与行为到计算模型与机器学习进行综合性的介绍。
Section 1 Introduction
Introduction to neuroscience, human cognition and behavior with computational model and machine learning.
Section 2 参数估计技术基础(3 学时)
介绍基本的参数估计技术。
Section 2 Basic Parameter Estimation Techniques
Introduction of basic parameter estimation techniques.
Section 3 参数估计技术基础的应用(3 学时)
基本的参数估计技术在人的认知行为建模中的应用。
Section 3 Application of Basic Parameter Estimation Techniques
Application of basic parameter estimation techniques in modeling human cognition and behavior.
Section 4 最大似然参数估计(3 学时)
主要介绍基本概率论、概率分布及最大似然参数估计技术。
Section 4 Maximum Likelihood Parameter Estimation
Introductions to probability distribution and maximum likelihood estimation.
Section 5 最大似然参数估计的应用(3 学时)
基本的参数估计技术在人的认知行为建模中的应用。
Section 5 Application of Maximum Likelihood Parameter Estimation
Application of Maximum Likelihood Parameter Estimation techniques in modeling human cognition and behavior.
Section 6 贝叶斯参数估计技术(3 学时)
主要介绍贝叶斯参数估计技术。
Section 6 Bayesian Parameter Estimation
Introduction to Bayesian parameter estimation techniques.
Section 7 贝叶斯参数估计技术的应用(3 学时)
贝叶斯参数估计技术在人的认知行为建模中的应用。
Section 7 Application of Bayesian Parameter Estimation.
Application of Bayesian parameter estimation techniques in modeling human cognition and behavior.
Section 8 多层或层级模型(3 学时)
主要介绍层级模型技术。
Section 8 Multilevel or Hierarchical Modeling.
Introduction to multilevel or hierarchical modeling techniques.
Section 9 多层或层级模型的应用(3 学时)
多层或层级模型技术在人的认知行为建模中的应用。
4
Section 9 Application of Hierarchical Modeling
Application of hierarchical model techniques in modeling human cognition and behavior.
Section 10 模型比较(3 学时)
主要介绍模型比较的方法。
Section 10 Model Comparison.
Introduction to computation model comparison method.
Section 11 心理学建模(4 学时)
主要介绍心理学建模与分析。
Section 11 Using Models in Psychology
Introduction to computation model and analysis in psychology.
Section 12 神经网络模型(4 学时)
主要介绍神经网络模型及其应用。
Section 12 Neural Network Models
Introduction to neural network models and its application on human cognition and behavior.
Section 13 神经科学模型(4 学时)
主要介绍神经科学模型及行为决策。
Section 13 Models in Neuroscience
Introduction of computational model in neuroscience and its application on decision-making.
期末汇报(6 学时)
学生在课堂上对小组的项目进行展示及讨论。
Final presentation
According to the group project in this semester, students present their research topics and communicate in class.
18.
教材及其它参考资料 Textbook and Supplementary Readings
Textbook
Computational Modelling of Cognition and Behavior, by Simon Farrell and Stephan Lewandowsky
Supplementary Readings
Machine Learning: A Probabilistic Perspective, by Kevin P. Murphy
Neuroscience: Exploring the Brain, by Mark F. Bear, Bear, Barry W. Connors, and Michael A. Paradiso
课程评估 ASSESSMENT
19.
评估形式
Type of
Assessment
评估时间
Time
占考试总成绩百分比
% of final
score
违纪处罚
Penalty
备注
Notes
出勤 Attendance
课堂表现
Class
Performance
5
小测验
Quiz
10
实时反馈学生课堂学习情况;
Give feedbacks of the course study
in the classroom.
课程项目 Projects
30
以小组汇报的形式完成课程项目,目
的培养学生小组合作能力;
Finish a team project via presentation
and help students to learn about
teamwork.
平时作业
Assignments
20
通过期中、期末总结,让学生回顾并
总结近半学习的学习内容以及学习收
获;
Through mid-term and final revision,
help students to summarize the
whole course and their results.
期中考试
Mid-Term Test
期末考试
Final Exam
期末报告
Final
Presentation
40
通过期末报告形式,培养学生独立汇
报能力;汇报内容与课堂学习内容相
关,考察学生对课程知识理解程度;
Help students to learn how to give
individual presentations through a
presentation test in the final exam, of
which contents will be highly related
to the course.
其它(可根据需
改写以上评估方
式)
Others (The
above may be
modified as
necessary)
20.
记分方式 GRADING SYSTEM
A. 十三级等级制 Letter Grading
B. 二级记分制(通/不通过) Pass/Fail Grading
课程审批 REVIEW AND APPROVAL
21.
本课程设置已经过以下责任人/员会审议通过
This Course has been approved by the following person or committee of authority