Guide-yakabatana mibvunzo · Zvakaoma Nhanho
Online uye Zvakaoma Negative Mining Quiz
Edzai pamhepo maringe nemadziva ekusina Indaneti, kusarudzwa kwebatch-hard uye semi-hard, zvinorasisa zvakaipa, uye cheki dzemumiriri.
Mubvunzo 1 ye 8
Nei mazhinji asina kurongeka akasarudzirwa zvakaipa achipa diki chiratidzo chekudzidzisa mukurasikirwa katatu?
Tarisa mubvunzo wese8 mibvunzo
Mhinduro uye tsananguro zvinoonekwa paunenge uchitora bvunzo.
- Nei mazhinji asina kurongeka akasarudzirwa zvakaipa achipa diki chiratidzo chekudzidzisa mukurasikirwa katatu?
- Kazhinji dzinonyorwa zvisirizvo
- Idzo iduku zvikuru kuti dzikwane mundangariro
- Ivo vatove kure neancho, saka kurasikirwa uye gradient zviri pedyo ne zero
- Vanogara vakaenzana nedaro rakanaka
- Chii chinosiyanisa kuchera padandemutande kubva pakuchera pasina Indaneti?
- Migodhi yepamhepo inoshandisa internet; offline haina
- Migodhi yepamhepo inosarudza mienzaniso yakaoma mukati meimwe mini-batch panhunzi
- Kuchera pamhepo kunoshanda chete pane zvinyorwa
- Kuchera pamhepo kunoda hapana kupfuudza
- Chii chinonzi 'semi-zvakaoma' chisina kunaka sekutsanangurwa kwazvinoitwa muFaceNet?
- A negative ari pedyo kupfuura positive kune anchor
- A negative inoenzana neancho chaizvo
- Chero akasarudzwa zvisina tsarukano
- A negative ari kure kupfuura positive asi achiri mukati memucheto
- Mune batch-hard mining, ndeipi isina kunaka inosarudzwa pane imwe neimwe anchor?
- Iyo yepedyo negative mubatch
- Iyo yekure yakaipa mubatch
- A random negative
- Iyo yakaipa ine kureba kwepakati
- Nei hombe batch saizi ichida kuvandudza mined metric-yekudzidza mhinduro?
- Inoderedza embedding dimension
- Inobvisa kudiwa kwemargin
- Inobvisa basa rekurasikirwa
- Inopa dziva rakapfuma remumiriri yakaoma negative padanho
- Ndeipi njodzi inozivikanwa yekusarudza zvakaomesesa zvakashata?
- Vanogara vari nyore
- Vanoita kuti batch matrix idiki
- Vanogona kunge vasina kunyorwa zvisizvo kana pedyo-duplicate zvakanaka izvo zvinokanganisa kudzidziswa
- Vanobvisa gradient zvachose
- With positive distance 0.4 and margin 0.2, which negative distance is semi-hard under the described rule?
- 0.5
- 0.2
- 0.8
- 1.1
- Why does ordinary online mining within one minibatch not necessarily find the hardest negative in the entire dataset?
- Every batch contains the complete dataset
- Its available candidate pool is the examples in that batch
- Distance calculations prove no other examples exist
- The model discards all negative labels