Topic 1 Question 57
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?
Increase the training data by adding variation in rotation for training images.
Increase the number of epochs for model training
Increase the number of layers for the neural network.
Increase the dropout rate for the second-to-last layer.
ユーザの投票
コメント(17)
NO CORRECT TRAINING DATA, MORE WORKS JUST WASTE TIME.
ONE OF THE REASONS FOR POOR ACCURACY COULD BE INSUFFICIENT DATA. THIS CAN BE OVERCOME BY IMAGE AUGMENTATION. IMAGE AUGMENTATION IS A TECHNIQUE OF INCREASING THE DATASET SIZE BY PROCESSING (MIRRORING, FLIPPING, ROTATING, INCREASING/DECREASING BRIGHTNESS, CONTRAST, COLOR) THE IMAGES.
ANSWER A. ADD MORE TRAINING DATA FOR ROTATION IMAGES COULD BE A WAY TO DEAL WITH ISSUE
👍 58DonaldCMLIN2021/09/22The answer is A!
👍 3eganilovic2021/11/03- 正解だと思う選択肢: A
A! How come all the answers this site gives out are incorrect?
👍 2apprehensive_scar2022/02/02
シャッフルモード