Loading...

Course Description

In this course, you will learn the fundamentals of neural networks, including how to adjust for different variables, train a neural network with backpropagation, and prepare images and text data for modelling.

Through demonstrations and applied learning, you will explore how to build a complete neural network architecture to solve different types of problems as well as how to improve a neural network’s performance.

You will also learn about proper techniques and best practices in training and validating clustering models through unsupervised learning. Finally, you will work through the complete process of solving a clustering problem and learn how to evaluate and improve the performance of clustering algorithms.

Earn a SAIT micro-credential

SAIT micro-credential badge

This course qualifies for the SAITMicro badge. Students who successfully complete this course with a final grade of A- or higher will earn a micro-credential and receive a shareable digital badge. Learn more

Learner Outcomes

Upon completion of this course, you will know how to:

  • prepare data (image or text) for modelling
  • build deep learning models to solve problems for an organization
  • evaluate the performance of deep learning model
  • build clustering models designed to solve problems for an organization
  • evaluate the performance of unsupervised learning models.

Prerequisites

DATA 024 - Supervised Learning — Regression, Univariate, and Multivariate Time Series is a mandatory requirement for this course. 

Applies Towards the Following Certificates

Loading...
Enrol Now - Select a section to enrol in
Section Title
Deep Learning and Unsupervised Learning
Type
Lecture - Online Synchronous
Days
T
Time
6:00PM to 7:00PM
Dates
Apr 01, 2025 to Apr 29, 2025
Schedule and Location
Contact Hours
24.0
Delivery Options
Blended  
Course Fee(s)
Tuition Fee non-credit $985.00
Section Notes

Prerequisites:

DATA 024 - Supervised Learning — Regression, Univariate, and Multivariate Time Series is a mandatory requirement for this course. 

Schedule: 

Participants will complete 24 hours of online, independent study supplemented with 6 hours of live virtual learning sessions with the instructor and other students. These virtual sessions are mandatory and will be delivered using Zoom & Brightspace/D2L and are interactive. Zoom sessions will be held on Tuesdays starting April 1, 2025 and ending April 29, 2025, from 6:00 pm - 7:00 pm. 

We encourage you to use your webcam and microphone to contribute to a more collaborative learning experience.

Required fields are indicated by .