Idanwo ti o sopọ mọ itọsọna · Alabọde Ipele

Didient Isọkale adanwo

Review plain gradient-descent direction, learning-rate steps, sampled gradients, momentum, Adam adaptation, numerical updates, and stationary-point limits.

Jẹmọ itọsọna awọn ọnaIsọkalẹ Ilọsiwaju
Ibeere 1 ti 8

In plain gradient descent, which direction is used relative to the objective's gradient?

Awotẹlẹ gbogbo ibeere8 ibeere

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

  1. In plain gradient descent, which direction is used relative to the objective's gradient?
    • The negative-gradient direction
    • The positive-gradient direction
    • An arbitrary perpendicular direction by definition
    • A direction chosen without evaluating any gradient
  2. Kini iṣakoso oṣuwọn ikẹkọ?
    • Awọn nọmba ti fẹlẹfẹlẹ ninu awọn awoṣe
    • Bawo ni ọpọlọpọ awọn kilasi awoṣe le ṣe asọtẹlẹ
    • Iwọn ti igbesẹ kọọkan ti o mu lakoko iṣapeye
    • Awọn iye ti ikẹkọ data lo
  3. How does a mini-batch gradient relate to the full selected training-data objective?
    • It uses no examples
    • It is computed on the batch and used as an estimate of the full-data gradient
    • It must equal the full-data gradient on every step
    • It only exists for images
  4. Isoro wo ni oṣuwọn ẹkọ ti o tobi ju le fa?
    • Ikẹkọ di o lọra pupọ ṣugbọn iduroṣinṣin
    • Awọn awoṣe foju awọn gradient
    • Eto data naa di ibajẹ
    • Awọn awoṣe overshoots awọn kere ati ki o le diverge
  5. What information does momentum carry into later gradient-descent updates?
    • Only the model's vocabulary size
    • A permanent deletion of all earlier gradients
    • A running weighted combination of earlier gradients
    • An unrelated random reset of every weight
  6. Kini ẹya bọtini kan ti oluṣapejuwe Adam ni akawe si isọkalẹ atẹle?
    • O ṣe atunṣe oṣuwọn ẹkọ ti o munadoko fun paramita kọọkan
    • O nlo igbesẹ ti o wa titi kan fun gbogbo paramita
    • Ko nilo awọn gradients
    • O nikan irin ni o wu Layer
  7. For plain gradient descent with old weight two, gradient three, and learning rate one-tenth, what is the new weight?
    • Two-point-three
    • One-point-nine-seven
    • Mẹta
    • One-point-seven
  8. What does a zero gradient fail to prove for a nonconvex training objective?
    • That the gradient value is zero at the evaluated point
    • That the current point is a global minimum
    • That the objective has been evaluated locally
    • That a stationary-point condition holds