Maswali yanayounganishwa na mwongozo · Kati Kiwango

Maswali ya Viwango vya Kujifunza kwa Mzunguko

Hukagua mizunguko ya viwango vya ujifunzaji vya pembetatu, jaribio la masafa, tabia ya kasi na tofauti kati ya mizunguko inayorudiwa na mafunzo ya mzunguko mmoja.

Njia za mwongozo zinazohusianaViwango vya Kujifunza kwa Mzunguko
Swali 1 ya 8

Ni dhana gani ya msingi ambayo viwango vya kujifunza kwa mzunguko vina changamoto?

Hakiki kila swali8 maswali

Majibu na maelezo huonekana unapojibu maswali.

  1. Ni dhana gani ya msingi ambayo viwango vya kujifunza kwa mzunguko vina changamoto?
    • Kwamba kiwango cha kujifunza kinapaswa kupungua tu wakati wa mafunzo
    • Ukubwa huo wa kundi lazima ubaki thabiti
    • Aina hizo zinahitaji GPU
    • Data hiyo lazima ichanganywe
  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. Je, 'Jaribio la masafa ya LR' hufanya nini?
    • Hupima matumizi ya kumbukumbu ya GPU
    • Huhesabu idadi ya vigezo vya mfano
    • Hufagia kiwango cha kujifunza kwenda juu huku ukitazama hasara ili kuchagua mipaka mizuri
    • Hujaribu muundo kwenye data ambayo haijasambazwa
  4. Katika sera ya mzunguko mmoja, kasi huwaje kwa kawaida ikilinganishwa na kiwango cha kujifunza?
    • Kasi inakaa fasta kote
    • Kasi imewekwa kuwa sifuri wakati wote
    • Kasi huongezeka sawasawa na kasi
    • Kasi husogea kinyume - juu wakati kasi iko chini na chini wakati kasi iko juu
  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. Ni nani aliyeanzisha viwango vya kujifunza kwa mzunguko na jaribio la masafa ya LR?
    • Geoffrey Hinton
    • Leslie Smith
    • Yann LeCun
    • Andrej Karpathy
  7. What sets the duration of a cyclical learning-rate cycle?
    • The number of model layers
    • Saizi ya msamiati
    • 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