Idanwo ti o sopọ mọ itọsọna · Alabọde Ipele

Idanwo Awọn enjini ti ara ẹni AI

Learn how recommender systems combine behavior, item features, candidate retrieval and ranking to tailor a list for one user.

Jẹmọ itọsọna awọn ọnaAI ti ara ẹni enjini
Ibeere 1 ti 8

Kini sisẹ ifowosowopo ni akọkọ da lori?

Awotẹlẹ gbogbo ibeere8 ibeere

Awọn idahun ati awọn alaye han bi o ṣe n mu ibeere naa.

  1. Kini sisẹ ifowosowopo ni akọkọ da lori?
    • Awọn awoṣe kọja ọpọlọpọ awọn olumulo, f.eks. 'Awọn eniyan ti o fẹran X tun fẹran Y'
    • Nikan apejuwe ọrọ ti nkan kọọkan
    • Ipele batiri ẹrọ olumulo
    • A ti o wa titi Olootu top-10 akojọ
  2. Kini 'iṣoro ibẹrẹ tutu' ni isọdi ara ẹni?
    • Awọn olupin ti o gun ju lati bata
    • Nini diẹ tabi ko si data nipa olumulo titun tabi ohun kan titun
    • Awọn iṣeduro ṣiṣẹ nikan ni igba otutu
    • Awọn olumulo n jade nigbagbogbo
  3. Ni aṣoju-ipele meji-ipele faaji, kini ipele akọkọ (iran oludije) ṣe?
    • Ni pato awọn ipo mẹwa nikan
    • Kọ awọn apejuwe ọja ikẹhin
    • Ni kiakia dín awọn miliọnu awọn ohun kan silẹ si awọn ọgọrun diẹ
    • Npa awọn akọọlẹ olumulo ti ko ṣiṣẹ
  4. Why might a recommender add a diversity objective to a ranked list?
    • To guarantee every item receives equal clicks
    • To remove all user-history signals
    • To make every recommendation random
    • To avoid filling the list with near-duplicate items and broaden the alternatives shown
  5. Kini 'awọn ifibọ' ninu eto iṣeduro kan?
    • Awọn oluṣoju awọn olumulo ati awọn ohun kan nitorina awọn ifihan agbara isunmọ ibaramu
    • Awọn eerun ti ara ni olupin naa
    • Awọn kuki ti a fipamọ sinu ẹrọ aṣawakiri
    • Imeeli koko ila
  6. Kini idi ti awọn esi ti ko boju mu (awọn titẹ, akoko aago) nigbagbogbo ṣe iwuwo pupọ lori awọn idiyele irawọ fojuhan?
    • O rọrun lati ṣe iro
    • O jẹ lọpọlọpọ lọpọlọpọ o si ṣe afihan ihuwasi gangan
    • O ti wa ni ti a beere nipa ofin
    • Star-wonsi ni o wa arufin
  7. What does content-based filtering use to recommend items?
    • Only other users’ passwords
    • Random item order
    • Features of items a user has liked or interacted with
    • The device’s battery history
  8. What does normalized discounted cumulative gain (NDCG) evaluate?
    • The number of users who created accounts
    • The model’s training duration
    • Whether an item description is grammatically correct
    • The quality of a ranked list, giving higher weight to relevant items near the top