search

Thunfischpirat / SpokenDigits

This is our submission for the final graded project for the WS22/23 course "Neural Networks: Theory and Implementation" at Saarland University.
1 stars 0 forks source link

Solve task II.3 of project. #12

Closed Thunfischpirat closed 1 year ago

Thunfischpirat commented 1 year ago

Use a dimensionality reduction algorithm such as t-SNE to analyze how the different models separate the different classes (the last non-linear layer in your model). Compare to the downsampled representation you used in the baseline and report your observations.

Thunfischpirat commented 1 year ago

We have yet to write code that performs t-SNE embedding for the linear model. This will require no tremendous extra effort.