CS280 Quiz1 (30 minutes)
Name:________________________
1. [20 marks] Use min-max normalization to normalize the following
sequence into range [10, 50]: 0, 3, 4, 5
2. [20 marks]Please calculate the cosine similarity between vectors
(1, 1, 1, 1) and (1, 2, 2, 0).
3. [15 marks]Please give the term frequency of term "software" in a
document with the following terms and number of
occurrences: (software, 20), (hardware, 10), (user, 30). The
representation (software, 20) denotes the term "software"
appears in the document 20 times.
AAA
AA
A
minnewminnewmaxnew
minmax
minv
v _)__(' +-
-
-
=
4. [15 marks]Please give the inverse document frequency of
term "software" in a set of 1000 documents where "software"
appears in 100 documents.
5. [15 marks]Given a set of 900 patients with 3 types of medical
problems: heart diseases, stress, and diabetes. Among the 900
patients, 300 have heart diseases, 300 have stress problems, and
300 have diabetes. Please calculate the entropy of the dataset.
6. [15 marks] Prove that the new sequence after z-normalization has
a mean of 0.
A
A
devstand
meanv
v
_
'
-
=