• 沒有找到結果。

CSIE 5043: Machine Learning

N/A
N/A
Protected

Academic year: 2022

Share "CSIE 5043: Machine Learning"

Copied!
21
0
0

加載中.... (立即查看全文)

全文

(1)

CSIE 5043: Machine Learning

Hsuan-Tien Lin

Dept. of CSIE, NTU

Course Introduction, 09/19/2011

(2)

Four Reasons for NOT Taking the Course (1/4)

Only English

English teaching

English homework writing English email communications English forum discussions

exception: Mandarin face-to-face discussions

If you are not comfortable withEnglish-teaching classrooms, ...

(3)

Four Reasons for NOT Taking the Course (2/4)

Complicated Contents

from a Taiwanese student taking MIT ML class (translated):

The professor started writing math equations as if he was using some writing accelerator. After class I always felt feeble. The worst part is: I needed to understand the contents as soon as I can. Otherwise I cannot finish the homework and cannot follow up in the next class.

NTU ML class: designed to beas good asthe best classes in the world

similar things will happen to you

If you are not willing to be somiserable, ...

(4)

Four Reasons for NOT Taking the Course (3/4)

Strict Instructor

Will you give me a second chance if I copy homework from other people? NO.

Could you let me pass because I will be kicked out by the 1=2 rule?NO.

Will you change my score from 59 to 60? NO.

Will you tolerate me to turn in my homework 10 minutes late? NO.

How many will pass? Any, if necessary.

(5)

Four Reasons for NOT Taking the Course (4/4)

Huge Loads

from a student taking ML class last year (posted on BBS):

lxxxxxx9: 作業光一小題就要我們test 100次?( 100*10min = 16hr) 唉 反 覆檢查許多遍 希望是我的code寫壞了 不然出這作業的人真的很沒良 心= =

our class: four to sixtimes harder than a normal one in NTU around seven homework sets (and a hard final project) homework due within two weeks

even have homework 0 and 1NOW already hard

no need to submit homework 0, but need to submit homework 1 If you do not want to spendso much time on homework, ...

(6)

May the Brave Ones Stay

(7)

Basic Information

instructor: Hsuan-Tien Lin (htlin@csie.ntu.edu.tw) office hour: after class or by appointment

course webpage: https://ceiba.ntu.edu.tw/1001ML announcements, homework, reference handouts, etc.

mailing list: supported by CEIBA

update your secondary email address on CEIBA

(8)

Enrollment

at most 98 in Room 102 readily have 98 now

new cases: sign up for the univ. lottery first, may adda fewmore in the third week if space allows

auditing: welcomed (to sit) only if there is an empty chair Drop as soon as possible!

Give your motivated classmates a chance to be miserable.

(9)

Teaching Assistants

ml2011ta@csie.ntu.edu.tw

TA Hour: Tuesdays 6:30pm to 7:30pm in R105

Ku-Chun Chou Polone Chen Yu-Cheng Chou Wei-Yuan Shen

Chun-Yen Ho Chung-Liang Li Yi-Hung Huang

Go to TA hours to discuss with TAs and classmates!

(10)

THE Book

Learning from Data

Y. Abu-Mostafa (Caltech), M. Ismail-Madgon (RPI), H.-T. Lin (NTU) idea initiated during ML2008

about 5 chapters out of 19 close to finalized, some more drafts coming in this term

teaching with the book, many homework problems within the book, reading assignments within the book

(11)

More about the Book

book forum and downloading : http://book.caltech.edu Your Privileges

learn from thefirst draft of the book download the draftfreely

Your Responsibilities

discuss with RPI studentsactively on the forum comment about the book on the forumbravely do not distribute the draft

enrolling in this class means agreeing to the items above

(12)

THE Principle

Taking any unfair advantages over other class members is not allowed. It is everyone’s respon- sibility to maximize the level of fairness.

eating? fine, but no smells and no noise sleeping? fine, but no snoring

cellphone? fine, but silent mode, and speak outside ...

applies to instructor, TAs, students

(13)

Honesty

NO CHEATING NO LYING NO PLAGIARISM

NO PIRATING of THE BOOK

very serious consequences

(14)

Grade

no midterm, no final

main reference: homework sets, final project fine-tune: participation in discussions

(15)

Collaboration and Open-Book

homework discussions: encouraged but fairness?

write the final solutions alone and understand them fully references (books, notes, Internet):

consulted, butnot copied from no need to lend/borrow solutions

to maximize fairness (everyone’s responsibility), lending/borrowing not allowed

(16)

Collaboration and Open-Book

to maximize fairness (everyone’s responsibility), lending/borrowing not allowed to maximize fairness (everyone’s responsibility),

lending/borrowing not allowed to maximize fairness (everyone’s responsibility),

lending/borrowing not allowed

Deal? If your classmate wants to borrow homework from you, what do you say?

(17)

Homework

students: justify solutions clearly TAs: evaluate solutions fairly penalty for late “parts”:

90% of value for 12-hour late, 80% one-day late, ...

10-min late is 12-hour late

(18)

Programming Assignments

about a third or half of the problems any programming language, any platforms uploadsource code and predictions, otherwise:

10% of value only!

no sophisticated packages students’ responsibility:

ask TA in advance for what can/cannot be used

(19)

Important TODOs

Update your secondary email address on CEIBA!

Sign the agreement form, and register on the forum (wait for approval).

Do homework 0 and 1; go to the TA hour for questions.

If you still want to be added, sign the form first (and try to enroll online) and wait for our decisions later.

May the Brave Ones Stay

(20)

One More Note on Discussions

book discussion: http://book.caltech.edu

—English

introduce yourself

download the sections and discuss

class discussion: simply use board learner@ptt2.cc

—English

email discussion: htlin@csie.ntu.edu.tw and TAs (ml2011ta@csie.ntu.edu.tw)

—English

face-to-face discussion: office hour with instructor, or TA hour

(21)

Questions?

參考文獻

相關文件

Hsuan-Tien Lin (NTU CSIE) Machine Learning Foundations 16/22.. If we use E loocv to estimate the performance of a learning algorithm that predicts with the average y value of the

Hsuan-Tien Lin (NTU CSIE) Machine Learning Techniques 5/22.. Decision Tree Decision Tree Hypothesis. Disclaimers about

main reference: homework sets, final project bonus 3%: participation in forum discussions.. Participation in

The study samples are students’ quiz grades , homework assignments (paper homework and English homework) and six comprehensive examinations.. It’s our hope that these conclusions

“Machine Learning Foundations” free online course, and works from NTU CLLab and NTU KDDCup teams... The Learning Problem What is

Hsuan-Tien Lin (NTU CSIE) Machine Learning Basics

Hsuan-Tien Lin (NTU CSIE) Machine Learning Techniques 3/24.:. Deep Learning Deep

Hsuan-Tien Lin (NTU CSIE) Machine Learning Techniques 21/22.. Matrix Factorization Summary of Extraction Models.