Ikibazo gihuza ibibazo · Hagati Urwego

Ibiciro byo Kwiga Cyikizamini Ikibazo

Kugenzura inyabutatu yo kwiga-igipimo cyizunguruka, ikizamini cyurwego, imyitwarire yihuta n itandukaniro riri hagati yinzinguzingo hamwe namahugurwa yumuzingi umwe.

Inzira zijyanye no kuyoboraIgipimo cyo Kwiga Cycle
Ikibazo 1 Bya 8

Ni ubuhe buryo bw'ibanze ibipimo byo kwiga byikurikiranya bigora?

Reba buri kibazo8 ibibazo

Ibisubizo nibisobanuro bigaragara mugihe ufata ikibazo.

  1. Ni ubuhe buryo bw'ibanze ibipimo byo kwiga byikurikiranya bigora?
    • Ko igipimo cyo kwiga kigomba gusa kugabanuka mugihe cyamahugurwa
    • Ingano yicyiciro igomba kuguma ihoraho
    • Izi moderi zikeneye GPUs
    • Ayo makuru agomba guhindurwa
  2. What did Smith report for cyclical learning rates on tested classification tasks?
    • They always lowered training loss to zero
    • They improved accuracy versus fixed rates, often in fewer iterations
    • They removed the need for validation data
    • They guaranteed escape from every sharp minimum
  3. 'Ikizamini cya LR' ikora iki?
    • Gupima imikoreshereze ya GPU
    • Kubara umubare wikitegererezo
    • Ihanagura igipimo cyo kwiga hejuru mugihe ureba igihombo kugirango uhitemo imipaka myiza
    • Gerageza icyitegererezo kuri hanze-yo gukwirakwiza amakuru
  4. Muri politiki yumuzingi umwe, ni gute imbaraga zisanzwe zitwara ugereranije nigipimo cyo kwiga?
    • Momentum igumaho hose
    • Momentum yashyizwe kuri zeru igihe cyose
    • Momentum yiyongera neza murwego hamwe nigipimo
    • Momentum igenda ihindagurika - hejuru iyo igipimo kiri hasi kandi kiri hasi mugihe igipimo kiri hejuru
  5. During a triangular cyclical learning-rate cycle, how does the rate move between its bounds?
    • It rises from the base rate to the maximum, then falls back toward the base
    • It only decreases from the first step
    • It stays fixed at the maximum
    • It jumps randomly at every minibatch
  6. Ninde watangije ibipimo byo kwiga byikizamini hamwe nikizamini cya LR?
    • Geoffrey Hinton
    • Leslie Smith
    • Yann LeCun
    • Andrej Karpathy
  7. What sets the duration of a cyclical learning-rate cycle?
    • Umubare wicyitegererezo
    • Ingano yamagambo
    • A chosen number of training iterations for the up-and-down pattern
    • The number of optimizer parameters
  8. What distinguishes the one-cycle policy from repeating several triangular cycles?
    • It keeps the learning rate constant throughout
    • It removes the optimizer’s momentum
    • It measures the learning rate only once
    • It uses one long learning-rate cycle for the training run