CS代考 COMP3308/COMP3608 Introduction to Artificial Intelligence (normal and advan

School of Computer Science
COMP3308/COMP3608 Introduction to Artificial Intelligence (normal and advanced)
semester 1, 2022
Unit coordinator and lecturer: Course web site on Canvas: https://canvas.sydney.edu.au/login/canvas (login with your unikey)

Copyright By PowCoder代写 加微信 powcoder

Welcome to COMP3308/3608 Artificial Intelligence!
Artificial Intelligence (AI) is all about programming computers to perform tasks normally associated with intelligent behaviour. Classical AI programs have played games, proved theorems, discovered patterns in data, planned complex assembly sequences and so on. This unit of study will introduce representations, techniques and architectures used to build intelligent systems. It will explore selected topics such as heuristic search, game playing, machine learning, neural networks and probabilistic reasoning. Students who complete this unit will have an understanding of some of the fundamental methods and algorithms of AI, and an appreciation of how these methods and algorithms can be applied to interesting problems. The unit will involve a practical component in which some simple problems are solved using AI techniques.
There are two streams: COMP3308 (regular) and COMP3608 (advanced). They share the same lectures, but have different tutorials and assessment. COMP3608 covers all the material of COMP3308, plus some extra topics, and also has more challenging assessments.
We hope that you will find this course interesting and useful!
Learning outcomes
At the completion of this unit, a student should be able to:
• Formulate problem space description, select and apply suitable search algorithms (brute-force and
heuristic) and analyse the issues involved
• Understand and apply minimax search and alpha-beta pruning in game playing
• Understand the basic principles and analyse the strengths, weaknesses and applicability of some of
the main AI algorithms for supervised learning, unsupervised learning and probabilistic reasoning
• Gain practical experience in designing, implementing and evaluating AI algorithms
• Present and interpret data and information in verbal and written form
• Appreciate some of the main ideas and views in AI, achievements and shortcomings of AI and the
links between AI and other Computer Science areas

1. Teaching team
Unit of study coordinator and lecturer
Associate Professor , Office: Computer Science Building, level 4, room 450
Teaching assistants
, , Closkey, , , ,
Moussa, ,
How to contact us
If you have questions about the course content, post them on the discussion board Ed Discussion, assessable via Canvas. This is the fastest way to get a response from the teaching team or your classmates. You can post your questions anonymously or not anonymously.
2. Timetable
• Lectures – online, via Zoom, live-streamed as “Zoom webinar”. Exception: a few lectures will be pre-recorded and available on Canvas in advance to watch during the lecture time.
• Tutorials COMP3308 – 2 modes: face-to-face and online (via Zoom) depending on your enrolment
• Tutorials COMP3608: only face-to-face
Lectures (start in week 1): Monday 10-12noon. Live-streamed via Zoom, except for a few pre-recorded lectures. The lectures will also be recorded, you can access them from “Recorded Lectures”.
Tutorials (start in week 2): Two modes depending on your enrolment: face-to-face or online; check your timetable. The online tutorials will be live-streamed via Zoom. One online tutorial will be recorded every week and made available on Canvas in “Recorded Lectures”. Please attend your allocated tutorial.
If you have technical issues with Zoom or other problems, you can attend another online tutorial. But this is an exception – you should attend your allocated tutorial.

Activity code (from your timetable)
face-to-face (CC)
Tutorial Time
Tutor Room
Wednesday 10-11
lecture room 275
Wednesday 11-12
school ABS seminar room 2290
Wednesday 13-14
school ABS seminar room 1080
Wednesday 14-15
school ABS seminar room 2003
Wednesday 15-16
Road learning hub seminar room LG16
Wednesday 16-17
school ABS seminar room 1080
Wednesday 17-18
school ABS seminar room 2290
Tuesday 16-17
school ABS seminar room 1100
Tuesday 16-17
seminar room 355
Tuesday 17-18
seminar room 355
Wednesday 14-15
hub seminar room 4001
online (RE)
Tuesday 16-17
Tuesday 17-18
Wednesday 10-11
Wednesday 11-12
Wednesday 13-14
Wednesday 15-16
Wednesday 16-17
Tuesday 16-17
face-to-face (CC), no RE
3. Course website
Wednesday 15-16
school ABS seminar room 1150
Wednesday 16-17
school ABS seminar room 1140
The main place for this course is the Canvas COMP3308/3608 website, accessible from: https://canvas.sydney.edu.au/login/canvas
We will use it for all teaching materials (lecture slides, tutorial notes and tutorial solutions), assignment specifications, submission of the weekly homeworks and posting of your marks.
In addition to Canvas, we will use two other systems: the discussion board Ed Discussion and the autograding system Grok. They will be linked to Canvas.

4. Weekly schedule
1 21 February
2 28 February
4 14 March
5 21 March
6 28 March
8 11 April
9 25 April
Introduction: administrative matters and course overview; what is AI, history and state of the art.
Problem solving and search. Uninformed search: BFS, UCS, DFS and IDS. Informed search 1 – greedy best-first.
Game playing: game playing as search; deterministic, perfect information, 0-sum games: minimax, alpha-beta pruning; non- deterministic games.
Introduction to machine learning. Instance-based learning. Rule-based methods.
Statistical-based learning.
Evaluating and comparing classifiers.
Decision trees.
Assignment 1 due: Friday 11.59pm
Introduction to neural networks. Perceptrons.
Multilayer neural networks 1.
Assignment 2 out: Monday
Mid-semester break
Multilayer neural networks 2.
Deep learning (Monday is a public holiday, the lecture will be pre-recorded, not live-streamed)
Support vector machines.
Ensembles of classifiers.
Assignment 2 due: Friday 11.59pm
Probabilistic reasoning. Bayesian networks and inference in them.
Unsupervised learning.
Applications of AI. Revision and preparation for the exam.
Homework No
No tutorial Yes
Yes Yes Yes Yes
Informed search 2: A*
Local search: hill-climbing, beam, simulated annealing, genetic algorithms.
Assignment 1 out: Friday
5. Assessment overview
Component Due date and submission Notes
Weekly Homeworks Weight: 4%
Tuesday 4pm, every week, except weeks 1 and 13
Individual Submitted in Canvas
No late submissions are allowed. The Canvas submission box will close at 4pm exactly, so submit earlier to avoid last minute problems.
Every week you are required to submit a homework using the submission box in Canvas before the tutorial classes. Exception: there is no homework in w1 (no tutorial) and w13 (last week of semester).
The homeworks for all students are due at 4pm on Tuesday (i.e. before the first COMP3308/3608 tutorial class), regardless of when your tutorial class is. This is fair as all students will have the same time to complete the homework. This is also the maximum possible time as the correct answers will be discussed at

the tutorials, and thus will be effectively available on Tuesday 4pm.
The homeworks are due in the current week, not the week after (as their goal is to prepare you for the tutorial), e.g. the homework for week 2 is due on Tuesday week 2, the homework for week 3 is due on Tuesday week 3, etc.
The homework exercises (typically 1 exercise) are clearly marked in the tutorial notes that you can download from Canvas. They are the same for both COMP3308 and COMP3608, unless otherwise specified.
The homework exercises are easy and require direct application of the material covered in the lectures in the current week. Their aim is to prepare you for the tutorial and also to encourage steady learning during the semester.
We will mark only 4 homeworks from the 11 homeworks that you will submit during the semester, for 1 mark each. These 4 homeworks will be randomly chosen but will be the same for all students. In week 13 we will inform you which homeworks were chosen for marking and we will also post the marks on Canvas.
Assignment 1 Weight: 12%
Friday week 7, 11.59pm Individual
Submitted in Grok
Late submissions: Late submissions are allowed up to 3 days late. A penalty of 5% per day late will apply. Assignments more than 3 days late will not be accepted (i.e. will get 0).
Given a problem, you will be required to apply one or more AI algorithms to solve it. This will include writing a computer program in Python to solve the problem. Only Python is allowed.
Assignment 2 Weight: 24%
Friday week 10, 11.59pm
Individual or in pairs (no more than 2 people). We encourage working in pairs. You can pair with a student from your tutorial or another tutorial.
Code – submit in Grok; report – submit in Canvas.
As in Assignment 1, but in addition to the computer program, you need also to submit a report presenting and analysing the results.
Assignments 1 and 2 will be posted on Canvas with information how to submit them in Grok.

Late submissions: late submissions are allowed up to 3 days late. A penalty of 5% per day late will apply. Assignments more than 3 days late will not be accepted (i.e. will get 0).
Exam Weight: 60%
Online, proctored Record+
During the exam period Individual
Exam duration: 2 hours
During exam period.
At least 40% on the exam is required to pass the course.
Information about the exam and a sample exam paper will be available in week 13.
Special considerations: If you experience short-term circumstances beyond your control, such as illness, injury or misadventure, which affect your preparation or performance in an assessment, you may apply for special consideration. There is a centralised University system; all applications are submitted online after login to “myUni” and are processed by the Student Administration Services unit.
Important: You are required to submit your special consideration application form within 3 working days from the date when the assessment was due. For more information see: http://sydney.edu.au/special- consideration
Passing this unit of study: The School of Computer Science has the following policy: To pass a unit of study, a student must achieve at least 40% in the written exam. A student must also achieve an overall final mark of 50 or more in order to pass a unit of study.
6. Availability of teaching materials
The course materials (lecture slides, tutorial notes and homework submission box) will be available every week in advance on Saturday morning on Canvas. For example, the materials for week 2 will be available on Saturday 9am in week 1.
The lecture slides initially will not include the answers to all questions and exercises that we will do during the lecture; the complete version with the answers will be uploaded after the lecture and available at 1pm on Monday.
The tutorial solutions will be available on Canvas on Wednesday 6pm. This is after the last tutorial on Wednesday which finishes at 6pm.

7. Academic honesty
All cases of plagiarism and academic dishonesty will be investigated. There is a centralized University system and database. Please read the University Policy on Academic Honesty carefully: http://sydney.edu.au/elearning/student/EI/academic_honesty.shtml
Please note that:
• If you copy from another student, website or other source, you have committed an act of plagiarism.
This includes copying the whole assignment or only a part of it.
• If you make your work available to another student to copy, you have committed an act of academic
dishonesty
• If you engage another person to complete your assignment (or a part of it), for payment or not, you have committed an act of academic misconduct. Your case will be forwarded to the University Registrar for investigation which is very serious.
The penalties for academic dishonesty, plagiarism and misconduct are severe and include: 1) a permanent record of academic dishonesty, plagiarism and misconduct in the University database and your student file, 2) mark deduction which varies from 0 marks for the assessment component to fail for the whole course, 3) expulsion from the University and cancelling of your student visa.
To detect plagiarism in reports (Assignment 2 report part), we will use TurnItIn, which is linked to Canvas.
To detect plagiarism in programming code we will use Grok’s similarity detection system. It is designed especially for detecting plagiarism in programming code. We will compare your programming assessments with these of other students (current and previous) and the Internet. The code similarity system is extremely good, e.g. it cannot be fooled by changing the variable names or the order of the conditions in if statements.
Please do not confuse legitimate cooperation with cheating. In individual assignments, you can discuss the assignment with another student, this is a legitimate collaboration, but you cannot complete the assignment together – everyone must write their own code and report.
Important: If someone asks you to see or copy your assignment, or to complete the assignment instead of them, just say: I can’t do this. This is against the University policy. I will not risk my reputation and future by doing this. Be smart and don’t risk your future by engaging in plagiarism and academic dishonesty!
8. Textbooks Textbook
. Russell and , Artificial Intelligence – A Modern Approach, 4th edition, Pearson, 2021. Recommended book
Ian H. Witten, , and . Pal, Data Mining – Practical Machine Learning Tools and Techniques, 4th edition, , 2017.
For both books you can also use the previous edition (the 3rd edition).

程序代写 CS代考 加微信: powcoder QQ: 1823890830 Email: powcoder@163.com