C2_W4_Assignment UNQ_C2 GRADED FUNCTION: softmax

Course Q&A Natural Language Processing NLP with Probabilistic Models
1

Hi
My softmax funtion output doesn’t match the expected output, no sure what’s wrong with it, and why do the expected outputs not sum p to 1?

Here is my softmax implementation:

# UNIT TEST COMMENT: Candidate for Table Driven Tests
# UNQ_C2 GRADED FUNCTION: softmax
def softmax(z):
  # mentor edit: code removed

and the output of the test:

Test the function

tmp = np.array([[1,2,3],
[1,1,1]
])
tmp_sm = softmax(tmp)
display(tmp_sm)

array([[0.09003057, 0.24472847, 0.66524096],
[0.33333333, 0.33333333, 0.33333333]])

array([[0.5       , 0.73105858, 0.88079708],
       [0.5       , 0.26894142, 0.11920292]])



When creating a post, please add:
* Week # must be added in the tags option of the post.
* Link to the classroom item you are referring to:
* Description (include relevant info but please do not post solution code or your entire notebook)

https://www.coursera.org/learn/probabilistic-models-in-nlp/programming/OrMrl/word-embeddings/lab?workspaceGatewayHost=hub.labs.coursera.org&path=%2Fnotebooks%2FC2_W4_Assignment.ipynb
2

Compare your code using around np.exp() with the equation you’re implementing. If I recall correctly, you may be missing a negative sign.

Also, please don’t post your code on the forum. That’s not allowed by the Code of Conduct.

3

Noted, thanks for pointing that out

4

I tried with a negative sign before z, but still not working…and my question still, why is the expected output in the assignment doesn’t sum up to 1.0?

5

The values in each row do add to 1.0.