Main

processing priority

3

site type

5 (wiki-type site, growing by topic rather than chronologically)

review version

11

html import

20 (imported)

Events

first seen date

2024-02-09 20:28:29

expired found date

-

created at

2024-06-06 17:59:18

updated at

2025-12-29 17:07:14

Domain name statistics

length

21

crc

48366

tld

86

nm parts

0

nm random digits

0

nm rare letters

0

Connections

is subdomain of id

87719371 (github.io)

previous id

0

replaced with id

0

related id

-

dns primary id

0

dns alternative id

0

lifecycle status

0 (unclassified, or currently active)

Subdomains and pages

deleted subdomains

0

page imported products

0

page imported random

0

page imported parking

0

Error counters

count skipped due to recent timeouts on the same server IP

0

count content received but rejected due to 11-799

0

count dns errors

0

count cert errors

0

count timeouts

0

count http 429

0

count http 404

0

count http 403

0

count http 5xx

0

next operation date

-

Server

server bits

server ip

-

Mainpage statistics

mp import status

20

mp rejected date

-

mp saved date

-

mp size orig

114242

mp size raw text

40896

mp inner links count

13

mp inner links status

20 (imported)

Open Graph

title

odie's whisper

description

image

site name

odie's whisper

author

updated

2025-12-17 11:06:48

raw text

odie's whisper odie's whisper 首頁 關於 標籤 分類 歸檔 漫談 Energy-based model 發表於 2021-06-01 | 分類於 energy-based model 基於能量模型(Energy-based model)是一種基於 能量函數 來定義機率模型的方式,能量函數是用來衡量變數的 可能性 ,為什麼這裡不是說是給出機率呢?因為能量函數的輸出是個實數,能量越小也代表可能性越高,如果要換算成機率就必須要考慮所有的可能性,除上 正規化項 才能讓這個值符合機率的要求,但求解這個正規化項往往是相當困難的 很多問題其實我們也不用真的去求出正規化項,能量函數已經足夠了,例如分類問題,實際上只需要讓你的目標類別是能量最低的,其他的類別能量提高即可,能量函數的設計相當彈性,所以很多問題其實都可以放入到 EBM 框架裡來解釋,Yann LeCun 大神在最近於 ICLR 2020 也給了個 Keynote 關於 Self-supervised learning 與 EBM 的 演講 ,與YT神人 Yannic Kilcher 線上討論 EBM ,還有最近有相當多的基於能量的生成模型,甚至都有 超越 GAN 的表現 ,這經典有點老派的 EBM 最近又熱了起來,趕緊來看看! Energy-based model 假設我們有一個參數為 $\theta$ 的能量函數 $E_\theta(x)$,將輸入變數$x$輸出一個代表能量的實數,所以可以定義出機率函數為 $$ p_{\boldsymbol{\theta}}(\mathbf{x})=\frac{\exp \left(-E_{\boldsymbol{\theta}}(\mathbf{x})\right)}{Z_{\theta}} $$ 為了要滿足機率的要求,定義正規化項 $Z_\theta$ 為各種可能的 x 下能量的總和 $$ Z_{\boldsymbol{\theta}}=\int \exp \left(-E_{\boldsymbol{\theta}}(\mathbf{x})\right) \mathrm{d} \mathbf{x} $$ 我們可以看到 $Z_\theta$ 是個很難求出的項,因為要把所有 x...

Text analysis

redirect type

0 (-)

block type

0 (no issues)

detected language

1 (English)

category id

Zastosowania AI (149)

index version

2025110801

spam phrases

0

Text statistics

text nonlatin

12597

text cyrillic

0

text characters

28211

text words

5482

text unique words

1911

text lines

1287

text sentences

16

text paragraphs

62

text words per sentence

255

text matched phrases

18

text matched dictionaries

2

RSS

rss path

rss status

3 (priority 3 already searched, no matches found)

rss found date

-

rss size orig

0

rss items

0

rss spam phrases

0

rss detected language

0 (awaiting analysis)

inbefore feed id

-

inbefore status

0 (new)

Sitemap

sitemap path

sitemap status

1 (priority 1 already searched, no matches found)

sitemap review version

1

sitemap urls count

0

sitemap urls adult

0

sitemap filtered products

0

sitemap filtered videos

0

sitemap found date

-

sitemap process date

-

sitemap first import date

-

sitemap last import date

-