PreReq quiz for Machine Learning for Healthcare (6.S897, HST.956)

This quiz will not count toward your grade, but will be used by the course staff to check prerequisites (6.036/6.862 or 6.867 or 9.520/6.860 or 6.806/6.864 or 6.438 or 6.034) and to assess students' preparation for this class.

Please submit it as soon as possible -- and no later than Tuesday 2/5/19 at 11:59pm EST. We expect the quiz to take no more than 15-20 minutes.

Email address *

Full Name (first, last) *

Your answer

Which of these MIT machine learning classes have you taken? *

6.867

9.520/6.860

6.806/6.864

6.438

6.034

6.036

6.862

Other:

Required

Consider the following generative process describing the joint distribution p(Z,X): Z ~ Bernoulli(0.2), X ~ Gaussian(mu_Z, 0.5), where mu_0=3 and mu_1=5. Which of the following plots is the marginal distribution p(X)? *

(A)

(B)

(C)

(D)

Consider the following one-dimensional dataset for the next two questions. There are two classes (blue circles and red squares).

[references image above] Where is the decision boundary of a (hard margin) linear SVM classifier trained on the full dataset? *

-2.5

-1.75

-1.5

-1

0

[references image above] What is the leave-one-out cross-validation error (i.e. average fraction of misclassified points from 6-fold cross-validation) for a hard-margin linear SVM classifier on this data? *

0

1/6

1/3

1/2

1

Gradient descent will always converge to a global minimum, even for non-convex functions. *

True

False

Please match the four values of C to the four figures. For each row (i.e. figure), select the column which corresponds to the correct value of C. *

C=0.1

C=1

C=10

C=100

Figure a

Figure b

Figure c

Figure d

What would be the value of output z in the neural network below for the input x1=1 and x2=0 ? *

-3

-2

-1

0

1

2

3

Please self-report which tasks you would be comfortable doing in Python for a given .csv of movies, cast list, genre, and box office gross numbers: *

Open the .csv file and read its content into a data structure.

Find average box office gross for horror movies in 2019.

Plot the cast list length versus box office gross.

Find frequent bi-grams in movie titles.

Fit a scikit-learn LinearRegression model to predict box office gross using all of the other features.

Determine the best hyperparameter C for the model using cross-validation.

Determine which feature is the strongest individual predictor of box office gross.

Required

Are you comfortable using Keras, TensorFlow, or PyTorch? *

Yes

No

What is your registration status as student for this class? *

MIT undergrad

MIT grad student

Non-MIT registered student

Why do you want to take this class? *

Your answer