Classifying objects in constellation images.
<p>a) Sample images from the original Fashion MNIST and MNIST datasets along with their constellations version below them. b) The plot shows the comparable classification accuracy of Humans and GenSearch algorithm on a test set of 38 images on both datasets c). Confusion matrix for classificat...
محفوظ في:
| المؤلف الرئيسي: | |
|---|---|
| مؤلفون آخرون: | , |
| منشور في: |
2025
|
| الموضوعات: | |
| الوسوم: |
إضافة وسم
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
|
| الملخص: | <p>a) Sample images from the original Fashion MNIST and MNIST datasets along with their constellations version below them. b) The plot shows the comparable classification accuracy of Humans and GenSearch algorithm on a test set of 38 images on both datasets c). Confusion matrix for classification in 1) Fashion MNIST for Humans 2) Fashion MNIST for GenSearch. The correlation between the two matrices is (Pearson’s coefficient) 0.79. Confusion matrix for 3) MNIST for Humans and 4) MNIST for Search Algorithm with a correlation of (Pearson’s coefficient) 0.70 between the matrices. We remove the entries when the corresponding elements are 0 in both matrices to calculate the correlation. Additionally, in many cases, humans don’t respond or give a response that does not correspond to any of the given options. Such responses are aggregated in the column ’Others’.</p> |
|---|