Question

imagine that you have opened the teachable machine app https://teachablemachine.withgoogle.com/ and train it to classify two kinds of objects, a pencil and an eraser. you then test it with your face and notice that it classifies your face as an eraser (60% eraser, 40% pencil). what are possible reasons for this? select all that apply. (choose two.)

when taking pictures of the eraser, your face also appeared in some of those pictures, but not in the pictures of the pencil.

your shirt is a similar color as the eraser.

when the model is not sure, or has a 50% probability assigned to both classes, it will default to the second of the two classes (in this case, the eraser).

there was some background noise (a dog barking) when you were taking pictures of the eraser, and also when you were testing the model with your face.

1 of 15 questions

Explanation:

1. For the first option: If the face appeared in eraser training images (not pencil), the model learns face features as part of eraser, so it classifies face as eraser.
2. For the second option: Similar shirt color to eraser can mislead the model, as it might associate the color (from face - shirt context) with eraser.
3. The third option is wrong: The model here has 60 - 40, not 50 - 50, so default logic doesn't apply.
4. The fourth option is wrong: Background noise (audio) doesn't affect image classification.

Answer:

A. When taking pictures of the eraser, your face also appeared in some of those pictures, but not in the pictures of the pencil.
B. Your shirt is a similar color as the eraser.