Idanwo ti o sopọ mọ itọsọna · Alabọde Ipele

Idanwo Ẹkọ Iwe-ẹkọ

Assess curriculum ordering, Bengio’s 2009 paper, self-paced learning, optimization hypotheses, and anti-curriculum. Check assumptions and scope.

Jẹmọ itọsọna awọn ọnaẸkọ iwe-ẹkọ
Ibeere 1 ti 8

What ordering does a common curriculum-learning strategy use?

Awotẹlẹ gbogbo ibeere8 ibeere

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

  1. What ordering does a common curriculum-learning strategy use?
    • Present examples from easier to harder according to a chosen schedule
    • Always present the most difficult example first
    • Sort examples alphabetically and never change the order
    • Use only examples that already have perfect predictions
  2. Tani o ṣe agbekalẹ ọrọ naa 'ẹkọ iwe-ẹkọ' ni iwe 2009 ti a mọ daradara?
    • Geoffrey Hinton
    • Yoshua Bengio ati awọn ẹlẹgbẹ
    • Andrew Ng
    • Yan LeCun
  3. Ni ẹkọ ti ara ẹni, tani pinnu iru apẹẹrẹ wo ni o jẹ 'rọrun' to lati ṣe ikẹkọ ni kutukutu?
    • Olutumọ eniyan ṣe aami iṣoro pẹlu ọwọ
    • Awọn hardware iṣeto
    • Awọn awoṣe funrararẹ, ti o da lori iru awọn apẹẹrẹ ni pipadanu kekere
    • Iyasọtọ iṣoro ti o ti ṣaju-oṣiṣẹ lọtọ nikan
  4. Kini idi ti ẹkọ iwe-ẹkọ le ṣe iranlọwọ iṣapeye?
    • O mu ki eko oṣuwọn laifọwọyi
    • O ṣe onigbọwọ aṣiṣe ikẹkọ odo
    • O yọ awọn nilo fun a isonu iṣẹ
    • O dan awọn ibi-afẹde ni kutukutu, ṣe iranlọwọ yago fun minima agbegbe ti ko dara
  5. How should a team test whether an easy-to-hard curriculum helps a model?
    • Compare against a suitable baseline with the same data and compute budget
    • Assume it helps whenever the schedule has more stages
    • Measure training loss once and skip held-out evaluation
    • Compare runs that use different data and different compute
  6. Kini ẹkọ 'egboogi-iwe-ẹkọ'?
    • Ikẹkọ laisi apẹẹrẹ rara
    • Fifihan awọn apẹẹrẹ lile ṣaaju awọn ti o rọrun
    • Lilo data afọwọsi nikan
    • Dipa isọdọtun
  7. Which four tasks did the 2010 self-paced learning paper report in its experiments?
    • Speech translation, protein folding, weather prediction, and music synthesis
    • Image captioning, game playing, robotics, and medical diagnosis
    • Object localization, noun-phrase coreference, motif finding, and handwritten-digit recognition
    • Clustering, sentiment analysis, machine translation, and speech diarization
  8. How can a curriculum be defined reproducibly?
    • Use the word “easy” without a criterion
    • Change the test set after each epoch
    • Select only examples the model already predicts correctly
    • Specify the example difficulty measure, ordering or schedule, and comparison baseline