Loading...

Description

Weekly webinars review key concepts and provide an opportunity for live interaction and Q&A with the instructors. The webinars will be recorded so if you are unable to attend you can watch the webinar recording at a time that is convenient to you.

Academic requirements

  • Required prerequisites:
    • Foundations of Data Science and Statistics for Data Science OR
    • A passing grade on the prior learning assessment, (PLA) conducted by the University of Toronto, for equivalent skills
    • If you are pursuing WatSPEED's AI Certificate, you don't need to complete the prior courses or the PLA to participate in this course.
    • However, learners enrolling in the AI Certificate Technical Track are expected to have prior knowledge and foundational skills in key areas including proficiency in Python, a basic understanding of linear algebra, familiarity with statistics and introductory probability, the ability to work with structured datasets, and comfort with core concepts such as regression and classification as well as correlation versus causation. For detailed information about prerequisites, please visit the AI Certificate page. 
  • A degree in Engineering, Mathematics, or Computer Science is recommended, but not required. Basic knowledge of programming and programming languages is strongly recommended.

System requirements

 

Receive a certificate from the University of Waterloo

Upon successful completion of this program, you will receive a professional education certificate from the University of Waterloo.

Who Should Enroll

 

  • Business associates, operations managers, project managers, and intelligence analysts.
  • Finance, securities, and insurance professionals.
  • Digital marketing and communication specialists.
  • Professionals from every level or industry who work with analytics or data.

What You Will Learn

Module 1: Introduction
  • Types of Machine Learning: Explore the different types of machine learning, including supervised, unsupervised, and reinforcement learning.
  • Challenges of Machine Learning: Understand the common challenges and complexities faced in machine learning.

Module 2: The Machine Learning Process: A Worked Example
  • Data Handling and Preparation: Learn how to collect, visualize, and share datasets effectively.
  • Data Preparation for Training: Master the steps for preparing data, including preprocessing and dividing into train/test/validation sets.
  • Model Selection and Training: Understand how to choose a model, tune hyperparameters, and train it.
  • Deployment and Monitoring: Learn the essentials of deploying, monitoring, and maintaining machine learning models.

Module 3: Classification
  • Binary Classification: Train models to classify data into two distinct classes.
  • Performance Measures: Discover various metrics to evaluate the performance of classification models.
  • Multiclass Classification: Learn techniques for classifying data into multiple categories.
  • Error Analysis: Understand how to analyze errors to improve model accuracy.
  • Multilabel Classification: Explore methods for handling data where multiple labels can be assigned to each instance.

Module 4: Unsupervised Learning and Clustering
 
  • Unsupervised Learning Basics: Define and understand the principles of unsupervised learning.
  • Clustering Objectives: Learn the objectives and techniques of clustering, including k-means, DBSCAN, and hierarchical clustering.
  • Clustering Algorithms: Explore various algorithms to group data points based on similarity.

Module 5: Training Models and Feature Selection
  • Regression and Classification with MLlib: Use MLlib for effective regression and classification tasks.
  • Sources of Error: Understand different sources of error, such as noise, bias, and variance, and how to handle them.
  • Regularization Techniques: Learn regularization methods to prevent overfitting and improve model generalization.

Module 6: Dimensionality Reduction
  • Curse of Dimensionality: Explore the challenges posed by high-dimensional data and how to address them.
  • Principal Component Analysis (PCA): Learn PCA for reducing dimensionality while retaining important information.

Module 7: Support Vector Machines (SVM)
  • Linear SVM Classification: Understand how to use linear SVM for classifying data.
  • Non-Linear SVM Classification: Explore non-linear SVM techniques for complex data patterns.
  • SVM Regression: Learn how SVM can be applied to regression problems for predicting continuous outcomes.

Module 8:  Decision Trees, Ensemble Learning, and Learning Forests
  • Decision Tree Training: Learn to train and visualize decision trees for data classification and regression.
  • Estimating Probabilities: Understand how to estimate probabilities and outcomes using decision trees.
  • Voting Classifiers: Explore how voting classifiers improve model performance by combining predictions.
  • Bagging, Boosting, and Stacking: Discover ensemble techniques like bagging, boosting, and stacking to enhance model accuracy.
  • Random Forest: Gain insights into Random Forests, a powerful ensemble method for classification and regression tasks.

Module 9: Introduction to Neural Networks and Keras
  • Neural Network Anatomy: Understand the structure of a neuron and the basics of neural networks.
  • Feedforward Neural Networks: Learn about feedforward neural networks and their applications in deep learning.
  • Activation Functions and Initialization: Explore various activation functions and techniques for initializing network weights.
  • Backpropagation: Master the backpropagation algorithm for training neural networks.
  • Building Neural Nets with Keras: Learn to build and train neural networks from scratch using Keras.
  • Fine-Tuning Neural Nets: Discover methods for fine-tuning neural networks to improve performance.

Module 10: Optimizing Deep Neural Networks
  • Gradient Problems: Understand vanishing and exploding gradient problems and how they affect deep networks.
  • Using Optimizers: Learn about advanced optimizers and their impact on model training.
  • Regularization Techniques: Explore techniques to avoid overfitting through effective regularization strategies.

Module 11: Using TensorFlow Interactively and Using Custom Functions
  • TensorFlow Fundamentals: Learn how TensorFlow works and its benefits for machine learning tasks.
  • TensorFlow Alternatives: Explore alternative tools and frameworks to TensorFlow for deep learning.
  • Interactive TensorFlow: Understand how to use TensorFlow interactively for dynamic model development.
  • Custom Functions: Learn to create and implement custom functions to enhance TensorFlow's capabilities.

Applies Towards the Following Certificates

Loading...

Enroll Now - Select a section to enroll in

Section Title
Machine Learning
Type
Online
Dates
May 25, 2026 to Aug 17, 2026
Course Fee(s)
Course Fee non-credit $1,199.00
Section Title
Machine Learning
Type
Online
Dates
Sep 28, 2026 to Dec 21, 2026
Course Fee(s)
Course Fee non-credit $1,199.00
Required fields are indicated by .