Útmutatóhoz kapcsolódó kvíz · Közepes Szint

Linear Algebra for Machine Learning Quiz

Practice matrix shapes, dot products, transposes and rank using concrete ML examples, and separate valid arithmetic from correct data meaning.

Kapcsolódó útmutató utakLinear Algebra For Machine Learning
kérdés 1 -ból 8

X has 100 rows and 3 feature columns, and w has shape 3 by 1. What is the shape of Xw?

Tekintse meg az összes kérdést8 kérdéseket

A válaszok és magyarázatok megjelennek a kvíz kitöltésekor.

  1. X has 100 rows and 3 feature columns, and w has shape 3 by 1. What is the shape of Xw?
    • 100 by 1
    • 3 by 100
    • 1 by 3
    • 100 by 3
  2. What result comes from the dot product [1, 2] · [2, −1]?
    • 4
    • 0
    • −2
    • 2
  3. X has rows [1, 2] and [3, 4]. Multiplying by [2, −1] gives which vector?
    • [2, −2]
    • [0, 7]
    • [0, 2]
    • [3, 7]
  4. A 5-by-2 matrix is transposed. Which dimensions result?
    • 5 by 2
    • 5 by 5
    • 2 by 2
    • 2 by 5
  5. A square feature matrix has two identical columns. What should a practitioner conclude about invertibility?
    • It lacks full column rank and is not invertible
    • It is invertible because it is square
    • Duplicating a column doubles the number of independent directions
    • Its inverse is its transpose
  6. Both AB and BA are defined for two matrices. What can be assumed about their values?
    • They must always be equal
    • They need not be equal
    • One must be all zeros
    • Both must be identity matrices
  7. A matrix-vector product returns finite scores without an error. What still needs verification before deployment?
    • Whether every matrix has an inverse
    • Whether all coefficients are integers
    • Feature meanings, units and column order
    • Whether the matrix contains only positive entries
  8. Why calculate a tiny matrix example manually before running a large pipeline?
    • To prove that all future data are representative
    • To avoid documenting the feature schema
    • To guarantee every matrix is nonsingular
    • To check axes and the intended operation against a known result