Download as docx, pdf, or txt
Download as docx, pdf, or txt
You are on page 1of 2

AI Software Developers COMP-377

Lab Assignment #5 – Apply LSTM algorithm to make future predictions


using time series data

Due Date: Sunday 11:59pm, Week 13

Purpose: The purpose of this Lab assignment is to:


 Build LSTM models to make future predictions using time series data
 Use TensorFlow for implementing LSTM models and evaluate their
accuracy

References: Read reference books and the lecture slides. This material provides the necessary
information that you need to complete the exercises.

Be sure to read the following general instructions carefully:


- This assignment must be completed individually by all the students.
- You will have to demonstrate your solution in a scheduled lab session and upload the
solution on eCentennial through the assignment link.

Exercise 1: LSTM

In this exercise you will implement an LSTM model to make future predictions using time series
data. Use TensorFlow to build an LSTM model for predicting stock prices for a company listed
in the NASDAQ listings.

Evaluate the model accuracy.

(5 marks)

Exercise 2: LSTM

In this exercise you will implement an LSTM model to generate text. Use a book from project
Gutenberg website, for example The Adventures of Tom Sawyer by Mark Twain:
https://www.gutenberg.org/files/74/74-0.txt. Use the LSTM model to generate new sequences of
characters. Then use a dataset with lyrics from a Canadian artist like Drake. Use the LSTM
model to generate new lyrics.

Evaluate the model accuracy.

(5 marks)

Evaluation:
Functionality: 85%
Correct implementation of requirements
Code explanation when asked

Lab #5 Page 1 of 2
AI Software Developers COMP-377

Algorithm design: correct design of classes and 15%


methods similarly to class examples and using
the naming guidelines.

Total 100%

You must name your Jupyter notebook file according to the following rule:
YourFullname_COMP377Labnumber_Exercisenumber.

Example: JohnSmith_COMP377La5_Ex1

Submission rules:

Submit your solution as a zip file that is named according to the following rule:
YourFullname_COMP377Labnumber.zip

Example: JohnSmith_COMP377Lab5.zip

Use 7-zip to compress files (https://www.7-zip.org/download.html).

Lab #5 Page 2 of 2

You might also like