Machine learning pytorch | Computer Science homework help

CMSC 510 HW2 –

The goal of the homework is to gain familiarity with PyTorch (to install it, see:
https://pytorch.org/get-started/locally/ ), a machine learning library for python that allows for
defining the machine learning model and performing gradient descent for it in an automated
way.

Complete 4 exercises described below, and submit via Canvas a zip file with four Jupyter
Notebook files, one per each exercise. Each notebook should contain the code, as well as short
reports on the results of experiments.

Exercise 1.

Train a linear classifier for the Iris dataset (a 3-class classification problem, file iris.csv in
Canvas), using Mean Squared Error as loss (see pytorch_linear_Iris_MSE.py file on Canvas).
Perform an analysis of the behavior of training risk and accuracy for different learning rates.

Detailed steps:
a) Use pandas to load the iris dataset. Create dummy variables for the classes

b) Define pytorch tensors for the dataset using:
torch.tensor

c) Define pytorch tensors (with gradient) for weights and biases (W & b). W should be
n_features x n_classes, b should be 1 x n_classes. Initialize b to zeros (torch.zeros), and W to
random values sampled from a normal distribution with null mean – try different values for the
standard deviation and observe changes in the training behavior.

d) Define pytorch optimizer over variables W & b
torch.optim.SGD or torch.optim.Adam

e) Create the main loop that goes over the dataset in multiple epochs. In each epoch
e1) clear gradients (using optimizer.zero_grad)
e2) calculate linear predictions: pred=X W + b using
torch.matmul
e3) pass the linear predictions through the unipolar sigmoid: sigmoid(pred)=1/(1+exp(-
pred)). Use these functions:
torch.log, torch.exp
e4) calculate the squared difference between the predictions (after sigmoid) and the
true classes, for all three output neurons. Use:
torch.pow
e5) calculate risk = average the squared difference over the training samples. Use:
torch.mean e6) calculate gradients of risk with respect to W & b (call risk.backwards)
e7) make optimizer step (using optimizer.step)
e8) calculate accuracy

Experiment with different learning rates for the two optimizers and report the behavior of the
training loss and accuracy.

Exercise 2.

Train a linear classifier for the Iris dataset, using CrossEntropy as loss. Perform an analysis of the
behavior of training risk and accuracy for different learning rates.

Detailed steps – follow Exercise 1, but replace MSE with CrossEntropy:

e3) pass the linear predictions through softmax (i.e., normalize the unipolar sigmoids for classes
i=1,…,3 to sum up to 1 for each sample)

e4) calculate the cross entropy after softmax (sum_{i=1}^3 y_i ln(softmax_i)).
torch.multiply, torch.log, torch.sum

e5) calculate risk = average the cross entropy over the training samples

Experiment and report results as in Exercise 1.

Exercise 3.

Starting from Exercise 2, add a split of the Iris dataset into a training set and a test set. Also, in
the training loop, go over small batches of samples (e.g. 20 samples) instead of always over the
whole training set. Experiment with batch size and learning rate.

Exercise 4:

Linear classifier for MNIST Digits dataset. Explore the behavior of the code from Exercise 3 on a
larger, more complicated dataset and report the results.
The number of training samples is 50,000 – analyze training behavior if a random subset of 100,
500, 1000, 2000 samples is used instead. Also, experiment with the learning rate and the batch
size.

For loading the dataset, use: import torchvision.datasets as datasets
full_train_dataset = datasets.MNIST(root=”./data”, train=True, download=True, transform=None)
full_test_dataset = datasets.MNIST(root=”./data”, train=False, download=True, transform=None)
x_train = full_train_dataset.data.numpy().reshape(-1,n_features).astype(dtype=np.float)/255.0;
x_test = full_test_dataset.data.numpy().reshape(-1,n_features).astype(dtype=np.float)/255.0;
y_train_cat = full_train_dataset.targets.numpy()
y_test_cat = full_test_dataset.targets.numpy()
Note that the download of the dataset may take long time. As with Iris, convert categorical
variables for classes into dummy variables (there are 10 classes).

Continue to order Get a quote

July 1, 2023

9.1 The United States in the International Economy

1) Following the tariff imposed on Chinese tires, some businesspeople correctly argued that the U.S. tariff would result in

A) China retaliating by raising tariffs on some U.S. exports.

B) China halting the sale of all products in the United States.

C) U.S. firms never being able to meet the demand for U.S.-produced tires.

D) the government demanding price cuts from U.S. tire manufacturers.

2) Workers in industries protected by tariffs and quotas are likely to support these trade restrictions because

A) they do not want to offend their employers who want them.

B) politicians lobby to convince workers the restrictions will make them better off.

C) they believe the restrictions will protect their jobs.

D) they don't understand that the restrictions will threaten their jobs.

3) The intention of the U.S. tariff on Chinese tires was to

A) protect jobs in the U. S. tire industry.

B) protect infant industries in tire U.S. tire market.

C) insure that Chinese tires meet U.S. quality and safety standards.

D) save the government money by restricting the sale of more expensive Chinese-made tires.

4) In the 1930s, the United States charged an average tariff rate ________. Today, the rate is ________.

A) of 100 percent; 20 percent

B) above 50 percent; less than 1.5 percent

C) of less than 10 percent; over 40 percent

D) of 17 percent; 33 percent

5) A tariff is a tax imposed by a government on

A) exports.

B) services.

C) imports.

D) luxury items.

6) Goods and services bought domestically but produced in other countries are referred to as

A) exports.

B) imports.

C) transfer payments.

D) foreign consumption.

7) Exports are domestically produced goods and services

A) sold to other countries.

B) sold to the government.

C) sold at home.

D) which are used to produce other goods and services.

8) When Roxanne, a U.S. citizen, purchases a designer dress from Barneys of New York that was made in Milan, the purchase is

A) both a U.S. and an Italian import.

B) a U.S. import and an Italian export.

C) a U.S. export and an Italian import.

D) neither an export nor an import for either country.

9) When BMW, a German company, purchases a welding machine that was made in Toronto, the purchase is

A) both a German and a Canadian import.

B) a German import and a Canadian export.

C) a German export and a Canadian import.

D) neither an export nor an import for either country.

10) Which of the following statements about the importance of trade to the U.S. economy is true?

A) Since 1950, both exports and imports have steadily decreased as a fraction of U.S. gross domestic product.

B) Overall, about 80 percent of U.S. manufacturing jobs depend directly or indirectly on exports.

C) The United States is the second largest exporter in the world.

D) The U.S. economy is highly dependent on international trade for growth in its gross domestic product.