Scalars, Vectors, Matrices & Tensors — Concept Check
Questions on Scalars, Vectors, Matrices & Tensors. Scalars, vectors, matrices and tensors are just numbers arranged in 0, 1, 2, and N dimensions — the containers that hold every piece of data an AI model ever sees.
Questions in this quiz
8 questions on Scalars, Vectors, Matrices & Tensors — Concept Check. Work through them here, then start the quiz to answer them and see your score.
1.You have a NumPy array with shape (64, 3, 32, 32). What type of data is this likely representing?
- AA vector of 64 elements
- BA batch of 64 RGB images
- CA matrix of 64x3 dimensions
- DA single grayscale image
2.In a neural network, you encounter a shape mismatch error between layers. What is a common cause?
- AInsufficient data samples
- BExcessive matrix rows
- CToo many scalar values
- DIncorrect tensor dimensions
3.A matrix has dimensions (10, 5). What does this represent in machine learning?
- A5 examples with 10 features each
- BA scalar value
- C10 examples with 5 features each
- DA single vector with 10 elements
4.You have a tensor with shape (128, 28, 28, 1). What does the '1' likely indicate?
- ASingle channel (grayscale) images
- BA scalar value
- CSingle feature vector
- DBatch size of 1
5.Which of the following is a scalar?
- Anp.array(7.0)
- Bnp.array([7.0])
- Cnp.array([[7.0]])
- Dnp.zeros((1,))
6.You need to extract the embedding of the first token from the first sentence in a tensor with shape (4, 10, 512). What is the shape of the extracted data?
- A(4, 512)
- B(1, 512)
- C(512,)
- D(10, 512)
7.A batch of RGB images is represented as a tensor with shape (32, 64, 64, 3). What does the '3' represent?
- ANumber of images
- BColor channels
- CHeight of images
- DWidth of images
8.What does the function `.ndim` return when called on a vector?
- A1
- B3
- C2
- D0