Scribd
Upload
2 views

Assignment_1

Uploaded by

saurabhchoudhary0701
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
2 views

Assignment_1

Uploaded by

saurabhchoudhary0701
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 1

Programming Assignment 1

Linear Regression using numpy


We will be using ipython notebooks for most of our assignments. You can refer
http://cs231n.github.io/ipython-tutorial/​ for installing the required software for working with
ipython notebooks and getting started with it. We will be using python ​2.7, ​so, please make sure
that the version you are using aligns with the that.
This assignment consist of a python notebook that depicts the outline of using linear regression
to learn a linear mapping function to map input data to the output. The function should be
learned with the objective to minimize the Mean Square Error (MSE) loss between the predicted
output and the ground truth data. The dataset for training and testing is being generated
randomly using a fixed seed. You have to fill all the missing parts which is indicated using
question marks (?) and hints wherever required (Use numpy operations wherever possible).
Please don't declare any function other than given in the notebook. The functions have their
usual meanings and is described below in brief. Some of the functions are partially implemented
and some of them are left for you to complete it.
● generate_dataset()​: It generates the dataset on the fly, to be used for training and
testing purposes.
● LinearRegression::forward()​: It computes the output using parameters of the network
and the input data. This is also called a forward pass of the linear regression network.
● LinearRegression::backward()​: It computes the gradients for every parameter of the
network and update the corresponding parameter using gradient descent step. This is
also called a backward pass as a prediction has been made and now the network is
updated accordingly, so as to minimize the loss function.
● MSELoss()​: It computes the Mean Squared Loss between the predicted output and
ground truth data. The formula for calculating the same has been discussed in the
lecture.
The algorithm to implement is mentioned in the comments, you have to use ​only ​numpy and
basic python functions and ​no​ other imports are allowed.

Submission: ​You have to submit a ipython notebook with the ​.ipynb​ extension. Please make
sure that all the cells are running. Please use the given ​Assignment_1.ipynb​ as a starting point
by uploading it to the jupyter notebook. You can complete the assignment gradually by
completing every cell and execute it in the order given. After completing the assignment, please
make sure that you are able to:
● visualize a plot between the loss function and training epochs.
● get training and test loss.
● visualize a learned function on the test data. This will be a plot where the test data will be
plotted as blue points and the red line indicates the learned function.
Outline of the results mentioned above has been implemented in the notebook, you just have to
complete the blanks. Please submit the completed file named as '​Assignment1_<Roll
No>.ipynb​'.

You might also like