Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Deep Learning: tutorial 3, possible zscore axis inconsistency with mathematical formulation #769

Open
alceballosa opened this issue Jul 12, 2021 · 0 comments
Labels
Content-Issue Problems and clarifications in the content (e.g., text, videos, slides)

Comments

@alceballosa
Copy link

Hi, I was reviewing the materials for W2D1_Tutorial3, specifically Section 2.1 (see the screenshot). This indicates that the mean and stdev are calculated for every stimulus (row-wise). However, in the corresponding code, zscore is applied across the columns (axis = 1, that is: for every neuron). Is this a mistake in the original code or am I interpreting things wrong?

imagen

Here is the code where the zscore function is called as part of the RDM function:

imagen

I believe the axis should be 0 so that the mean and stdev are calculated for the responses to each stimuli, but I'm not 100% sure.

Thanks in advance!

@spirosChv spirosChv added the W2D1 label Jan 16, 2022
@spirosChv spirosChv added the Content-Issue Problems and clarifications in the content (e.g., text, videos, slides) label Jan 26, 2022
@spirosChv spirosChv changed the title W2D1: tutorial 3, possible zscore axis inconsistency with mathematical formulation Deep Learning: tutorial 3, possible zscore axis inconsistency with mathematical formulation Jun 18, 2022
@spirosChv spirosChv added W1D5 and removed W2D1 labels Jun 18, 2022
@spirosChv spirosChv removed the W1D5 label Jul 6, 2023
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
Content-Issue Problems and clarifications in the content (e.g., text, videos, slides)
Projects
None yet
Development

No branches or pull requests

2 participants