Cambrian College
Log in Sign up

Applied Machine Learning Bootcamp

DIGI 004
Closed
SAIT
SAIT
Calgary, Alberta, Canada
BA
Bradley Ackroyd
Project Coordinator, School for Advanced Digital Technology
(2)
3
Timeline
  • June 14, 2021
    Experience start
  • June 15, 2021
    Project Scope Meeting
  • July 21, 2021
    Experience end
General
  • Bootcamp
  • 13 learners; individual projects
  • 60 hours per learner
  • Dates set by experience
  • Learners self-assign
Preferred companies
  • 1/13 project matches
  • Anywhere
  • Academic experience
  • Any
  • Any industries
Categories
Data analysis
Skills
data mining and analysis supervised and unsupervised learning algorithms machine learning
Project timeline
  • June 14, 2021
    Experience start
  • June 15, 2021
    Project Scope Meeting
  • July 21, 2021
    Experience end
Overview
Learner goals and capabilities

The Southern Alberta Institute of Technology and Braintoy are partnering in the delivery of a 12 week Applied Machine Learning Bootcamp. Our students engage in an individual final machine learning project that spans 3 weeks. This project culminates in the development of a machine learning model that predicts, detects, or forecasts an entity. The data for the use case could be images (computer vision), text (natural language processing), time series (multi-variate or univariate), or tablular data. The data format would be a folder of images or comma-separated values (CSVs) for text, time series, or tablular data. The client will need to:

1) Provide a clearly defined machine learning problem.

2) Explain how the client intends to use the solution.

3) Explain why this problem needs to be solved.

4) Provide a subject matter expert that can be a touch point for the student and answer questions related to the data and use case.

Expected outcomes and deliverables

Students will produce a proof of concept, predictive machine learning model (i.e. a minimally viable product) that solves a client problem.

Project Examples

Examples of student-developed predictive machine learning models:

  • Electricity consumption predictions or electricity load forecasting.
  • Facial recognition.
  • Solar power generation prediction.
  • Oil production prediction.
  • Carbon emission prediction.
  • Heart attack prediction.
  • Credit fraud detection.
  • Predicting customers who are a potential flight risk (customer churn).
  • Using MRI images to detect and predict patients who may have brain tumor.
  • Using chest ray images of patients to predict patients who are at risk of getting covid.
Additional company criteria

Companies must answer the following questions to submit a match request to this experience:

Be available for a quick phone call with the instructor to initiate your relationship and confirm your scope is an appropriate fit for the course.

Provide a dedicated contact who is available to answer periodic emails or phone calls over the duration of the project to address students' questions.