nerdexam
Amazon

MLS-C01 · Question #73

A Machine Learning Specialist is required to build a supervised image-recognition model to identify a cat. The ML Specialist performs some tests and records the following results for a neural…

The correct answer is A. Increase the training data by adding variation in rotation for training images. The ML Specialist notices that, in over 75% of the misclassified images, the cats were held upside down by their owners.

Modeling

Question

A Machine Learning Specialist is required to build a supervised image-recognition model to identify a cat. The ML Specialist performs some tests and records the following results for a neural network-based image classifier:

Total number of images available = 1,000 Test set images = 100 (constant test set) The ML Specialist notices that, in over 75% of the misclassified images, the cats were held upside down by their owners. Which techniques can be used by the ML Specialist to improve this specific test error?

Options

  • AIncrease the training data by adding variation in rotation for training images.
  • BIncrease the number of epochs for model training
  • CIncrease the number of layers for the neural network.
  • DIncrease the dropout rate for the second-to-last layer.

How the community answered

(29 responses)
  • A
    76% (22)
  • B
    3% (1)
  • C
    7% (2)
  • D
    14% (4)

Explanation

The ML Specialist notices that, in over 75% of the misclassified images, the cats were held upside down by their owners.

Topics

#Data Augmentation#Image Classification#Model Robustness#Test Error Analysis

Community Discussion

No community discussion yet for this question.

Full MLS-C01 Practice