Ikibazo gihuza ibibazo · Hagati Urwego
Ikibazo Cyifuzo cya AI Ikibazo
Ongera usuzume uburyo bwo gutanga ibyifuzo, gufatanya no gushungura ibiyirimo, matrix matrixisation, sisitemu ya Hybrid, hamwe ningaruka zo gusezerana.
Ikibazo 1 Bya 8
Ni iki 'gufatanya gushungura' gishingiye ku gutanga ibyifuzo?
Reba buri kibazo8 ibibazo
Ibisubizo nibisobanuro bigaragara mugihe ufata ikibazo.
- Ni iki 'gufatanya gushungura' gishingiye ku gutanga ibyifuzo?
- Ibishushanyo kubakoresha benshi bafite uburyohe busa
- Ibisobanuro byanditse kuri buri kintu gusa
- Igiciro cyibicuruzwa
- Urutonde ruhamye top-10 urutonde
- Ibirimo bishingiye ku kuyungurura birasaba ibintu ahanini na:
- Icyitegererezo cya kataloge
- Guhuza ibintu biranga ibyo ukunda kera
- Kubara igurishwa rusange
- Gusaba abandi bakoresha gutora
- What did the Netflix Prize seek to improve by 10% over the Cinematch baseline?
- Click-through rate for every recommended film
- The number of films watched per user
- Root mean squared error (RMSE) on the competition’s held-out ratings
- A user’s average watch time on the service
- Muri matrix factorisation, abakoresha nibintu byerekanwe nka:
- Yego yego / oya ibendera
- Isubiramo ryanditse
- Amatariki ya Kalendari
- Ibice byihishe 'ibintu byihishe'
- What mechanism did the Deep Interest Network paper propose for modeling a user’s different interests across candidate ads?
- A local activation unit that forms a candidate-specific interest representation
- A fixed user vector that is identical for every candidate
- A rule that selects only the most popular ad
- A graph algorithm that proves every ad is relevant
- Icyifuzo cya 'hybrid' ni kimwe muri:
- Gusa ikora muri wikendi
- Ihuza uburyo bwo gufatanya nuburyo bushingiye kubirimo
- Ntabwo ikoresha amakuru na gato
- Tanga gusa ibintu bishya gusa
- What is one limitation of collaborative filtering for a new item with no interactions?
- It cannot use ratings
- It requires item descriptions only
- It may lack the interaction data needed to recommend the item
- It always recommends every new item
- What should a recommender evaluation measure besides click-through rate?
- Only the model’s parameter count
- Only training loss
- Only the number of recommendations
- User outcomes and harms such as diversity, exposure, or unwanted engagement