๐Ÿข ETRI (2024.01.15)

๐Ÿ“Œ 01.12-TODO List:

1. ๋…ผ๋ฌธ review: A Free Lunch for Unsupervised Domain Adaptive Object Detection without Source Data
โˆ™ ๋…ผ๋ฌธ ์ •๋ฆฌ
โˆ™ ๋…ผ๋ฌธ review
โˆ™ PPT๋งŒ๋“ค๊ธฐ


2. ์ฃผ์ค‘์— ํ•  ๊ฒƒ: Deep Learning 2024(Bishop)-Chapter 2 ์ฝ๊ณ  ๊ณต๋ถ€ํ•˜๊ธฐ
โˆ™ 2.1  The Rule of Probability
โˆ™ 2.2  Probability Densities
โˆ™ 2.3  The Gaussian Distribution
โˆ™ 2.4  Transformation of Densities
โˆ™ 2.5  Information Theory
โˆ™ 2.6. Bayesian Probabilites
AAAI์— ๋„ฃ์„ ๋‚ด์šฉ์œผ๋กœ ์ •๋ฆฌ ๋ฐ Exercise ํ’€๊ธฐ

3. ์ฃผ์ค‘์— ํ•  ๊ฒƒ: Deep Learning 2024(Bishop)-Chapter 3 ์ฝ๊ณ  ๊ณต๋ถ€ํ•˜๊ธฐ
3.1. Discrete Variables
3.2. The Multivariate Gaussian
3.3. Periodic Variables
3.4. The Exponential Family
3.5. Nonparametric Methods
 

A Free Lunch for Unsupervised Domain Adaptive Object Detection without Source Data | Proceedings of the AAAI Conference o

 

ojs.aaai.org

 

 
 


 
 

 
 

๐Ÿš ์ถœ๊ทผ! (8:10 - 8:25)

๊ทธ๋ƒฅ 7์‹œ์— ์•Œ๋žŒ ๋งž์ถฐ๋ฒ„๋ ธ๋‹ค ใ…‹ใ…‹ใ…‹
๊ทธ๋ž˜๋„ ๋ฐฅ์€ ๋ง›์žˆ๊ฒŒ ์•ผ๋ฌด์ง€๊ฒŒ ๋จน๊ณ ์™”๋‹ค ํžˆํžˆ๐Ÿคฃ
์ถœํ‡ด๊ทผ์€ ์…”ํ‹€๋ฒ„์Šค๊ฐ€ ์—ญ์‰ฌ ์ œ์ผ ๋น ๋ฅธ๊ฑฐ ๊ฐ™๋‹ค. (Shortest Path Algorithm?)
 
 

 
 
 
 

๐Ÿ“– ๊ณต๋ถ€! (8:30-12:00)

์…”ํ‹€๋ฒ„์Šค ํƒ€๊ณ  ์˜ค๋Š”๊ฒŒ ์ผ์ฐ๊ณต๋ถ€ํ•  ์ˆ˜ ์žˆ์–ด์„œ ์ด๋“์ธ๊ฑฐ ๊ฐ™๋‹ค.
์ด์ œ ๋‚จ์€ ํ• ์ผ:
โˆ™ ๋…ผ๋ฌธ review:
     ๋…ผ๋ฌธ ์ •๋ฆฌ
     ๋…ผ๋ฌธ review
     PPT๋งŒ๋“ค๊ธฐ

โˆ™ Deep Learning(Bishop 2024): Chapter 3 ์ด๋‹ค.
3.1. Discrete Variables
3.2. The Multivariate Gaussian
3.3. Periodic Variables
3.4. The Exponential Family
3.5. Nonparametric Methods
 
์•„ ๊ทธ๋ฆฌ๊ณ  ๋„ˆ๋ฌด ๋’ท๊ณจ ๋•ก๊ธฐ๊ณ  ๋ชฉ์•„ํ”„๊ณ  ๋จธ๋ฆฌ์•„ํŒŒ์„œ
์งœ์ž”- ์˜›๋‚ ์— ๋‹ค์ด์†Œ์—์„œ ์‚ฐ ๋ชฉ ๋งˆ์‚ฌ์ง€ ๊ธฐ๊ตฌ๋ฅผ ๋“ค๊ณ ์™”๋Š”๋ฐ ๊ฒจ์šฐ ์‚ด๋งŒํ–ˆ๋‹ค.
๊ทธ๋ž˜๋„ ๋‚˜๋ฆ„ ํšจ๊ณผ๊ฐ€ ์ค€์ˆ˜ํ•˜๋‹ค?
 
์•„...ํ• ๊ฑฐ ๋“œ~~~๋ฆ…๊ฒŒ ๋งŽ๋‹ค ์ง„์งœใ…‹ใ…‹๐Ÿ˜ฑ
 
 
 
 
 

๐Ÿš ๋ฐฅ์ด๋‹ค ๋ฐฅ! (12:30~13:00)

๋งˆ์ฐฌ๊ฐ€์ง€๋กœ ๋™ํŽธ์ œ(ํ•œ์‹):๊ฐœ๋…ธ๋ง›...
 
 

 
 
 
 

 
 

๐Ÿ“– ๋…ผ๋ฌธ๋ฐœํ‘œ! (14:30-18:00)

๋งŽ์ด ๋ฐฐ์šฐ๊ธด ๋ฐฐ์› ๋Š”๋ฐ ๊ทธ๋งŒํผ ํž˜๋“ ์‹œ๊ฐ„...
๊ทธ๋ž˜ํ”„ํ•˜๋‚˜ํ•˜๋‚˜, ์‹ ํ•˜๋‚˜ํ•˜๋‚˜ ์ €์ž์˜ ์˜๋„ํŒŒ์•… ๋ฐ ๋น„ํŒ์ ์‚ฌ๊ณ ? ์ฝ”๋“œ๊ตฌํ˜„๊ฐ€๋Šฅ์„ฑ ์ด๋Ÿฐ๊ฑธ ์ž˜ ๋ด์•ผํ•œ๋‹ค๋Š”๊ฑธ ๊นจ๋‹ฌ์•˜๋‹ค
 

 
 

 

๐Ÿš ํ‡ด๊ทผ! (18:30 - 19:00)

ํ‡ด๊ทผ์ด ์ œ์ผ ์ข‹๋‹ค๋Š” ์ง์žฅ์ธ์˜ ๋ง์— ๊ณต๊ฐ์ด ์ ์ ๋œ๋‹คใ…‹ใ…‹ใ…‹
์•„์นจ์ถœ๊ทผ๋•Œ๋ฌธ์— ๊ทธ๋ƒฅ ์กธ๋ฆฌ๋‹คใ…‹ใ…‹ ํ”ผ๊ณค๐Ÿฉธํ•˜๊ณ ใ… ใ… 


 
 
 
 

๐Ÿ‹๐Ÿป ์šด๋™! (19:00 -)

์–ด์ œ 3๋Œ€ 400 (S:150 , B: 92.5, D:157.5) ๊น”์Œˆํ•˜๊ฒŒ ์ฐ์–ด์„œ ๊ทธ๋Ÿฐ์ง€ ๊ธฐ๋ถ„์ด ์ข‹๊ตฌ๋งŒ!!๐Ÿ˜ค

400 ์ฐ์—ˆ์œผ๋‹ˆ? ์ด์ œ 3๋Œ€ ์šด๋™๋ณด๋‹จ ์ข€ ๋” ์„ธ๋ถ„ํ™”ํ•ด์„œ A,B๋ฃจํ‹ด ์•ˆํ•˜๋Š” ๋‚ ์—๋Š” ๊ฐ€์Šด,์‚ผ๋‘, ๋“ฑ,์ด๋‘, ์–ด๊ป˜ ์œ„์ฃผ๋กœ ํ•ด๋ด์•ผ๊ฒ ๋‹ค.
 
 

๐Ÿ‹๐Ÿป ์šด๋™ ์›”๊ฐ„ ๊ณ„ํš:

A→(๋ฒค์น˜,์‚ผ๋‘)→B→(๋ฐ๋“œ+๋“ฑ,์ด๋‘)→A→(๋ฒค์น˜,์‚ผ๋‘)→B→
(๋ฐ๋“œ+๋“ฑ,์ด๋‘)→A→(๋ฒค์น˜,์‚ผ๋‘)→B→(๋ฐ๋“œ+๋“ฑ,์ด๋‘)→A→(๋ฒค์น˜,์‚ผ๋‘)→
B→(๋ฐ๋“œ+๋“ฑ,์ด๋‘)→A→(๋ฒค์น˜,์‚ผ๋‘)→B→(๋ฐ๋“œ+๋“ฑ,์ด๋‘)→A→
(๋ฒค์น˜,์‚ผ๋‘)→B→(๋ฐ๋“œ+๋“ฑ,์ด๋‘)→A→(๋ฒค์น˜,์‚ผ๋‘)→B→(๋ฐ๋“œ+๋“ฑ,์ด๋‘)→
 

๐Ÿ‹๐Ÿป ์ด๋ฒˆ์ฃผ:

(๋ฐ๋“œ+๋“ฑ,์ด๋‘)→A→(๋ฒค์น˜,์‚ผ๋‘)→B→(๋ฐ๋“œ+๋“ฑ,์ด๋‘)→A→(๋ฒค์น˜,์‚ผ๋‘)
 

๐Ÿ‹๐Ÿป ์˜ค๋Š˜: (๋ฐ๋“œ+๋“ฑ,์ด๋‘)

๋ฐ๋“œ: 80,90,100  (7,5,3)
๋ฐ”๋ฒจ๋กœ์šฐ: 40,50,60  (10,10,10)
์™€์ด๋“œ๋ฐ”๋ฒจ์ปฌ: 30์”ฉ 5์„ธํŠธ
ํด๋กœ์ฆˆ๋ฐ”๋ฒจ์ปฌ: 25์”ฉ 5์„ธํŠธ

๋ฐ๋“œ: 120 1ํšŒ
 

 
 

๐Ÿ“Œ TODO List:

1. ๋…ผ๋ฌธ์ €์ž์—๊ฒŒ ๋ฉ”์ผ๋ณด๋‚ด๊ธฐ!




2. ์ฃผ์ค‘์— ํ•  ๊ฒƒ: Deep Learning 2024(Bishop)
- Chapter 2: Exercise ํ’€๊ธฐ.

- Chapter 3 ์ฝ๊ณ  ๊ณต๋ถ€ํ•˜๊ธฐ
3.1. Discrete Variables
3.2. The Multivariate Gaussian
3.3. Periodic Variables
3.4. The Exponential Family
3.5. Nonparametric Methods

3. Student t๋ถ„ํฌ ๋ฐ ๊ฐ€์„ค๊ฒ€์ • ๋‹ค์‹œ ๊ณต๋ถ€ํ•˜๊ธฐ.


 

'2024 winter > ETRI(์ผ์ƒ)' ์นดํ…Œ๊ณ ๋ฆฌ์˜ ๋‹ค๋ฅธ ๊ธ€

[ETRI]2024.01.17  (0) 2024.01.17
[ETRI]2024.01.16  (0) 2024.01.16
[ETRI]2024.01.12  (2) 2024.01.12
[ETRI]2024.01.11  (0) 2024.01.11
[ETRI]2024.01.10  (4) 2024.01.10

+ Recent posts