Foundations of Machine Learning

Join today
  • Instructor:  Akshay Ghosh
  • Level: Beginner
  • Duration: 3 hours
  • Helpers: TBD
  • Date:  March 14, 2025 | 1:30 – 4:30 PM (Atlantic)
  • Prerequisite: Foundational understanding of general Python programming skills.
Empty space, drag to resize
COURSE DESCRIPTION

Join ACENET for an introductory session that explores the fundamentals of machine learning and its applications.

We’ll break down key terminology—machine learning, deep learning, and neural networks—so you can confidently navigate the field. You'll learn about essential methods, from simple models like Linear Regression and Decision Trees for classification to more advanced techniques such as Support Vector Machines and Neural Networks—the foundation of Large Language Models. We’ll also discuss practical considerations for setting up a machine learning project, including the resources you need, data collection strategies, factors that contribute to success, and lessons to take away when things don’t go as planned.


Bring your questions and join the conversation!

SETUP REQUIREMENTS
  • See instructions for how to download and setup Python here.

Meet our team!

Akshay Ghosh

Instructor

Research Consultant
MSc Astrophysics, Saint Mary's University

Akshay, based in Halifax, joined ACENET in 2023. He is skilled in Python, MATLAB, Unix shell scripting, and R, with teaching experience as a physics and astronomy teaching assistant involving course material creation and lab supervision. His research during his MSc in Astrophysics focused on time series analysis of Active Galactic Nuclei. He developed a new method using wavelet analysis, resulting in a first-author publication.

Tannia Chevez

Host

Digital Training Specialist
BSc Computational Chemistry, Memorial University

Tannia joined ACENET in 2023 and is based in St. John’s. She has held positions as a research assistant in various departments, with responsibilities ranging from developing algorithms for an online animal sound repository, to crafting chemical composite films. Proficient in Python, Java, and JavaScript, she has focused on spectral data analysis, SEM image-based nanoparticle detection, and software development for data analysis. Tannia contributed significantly to the publication of a research paper by analyzing potential environmental toxicants, generating millions of chemical structure IDs, and conducting data extraction and analysis using Python, R, and JavaScript, as well as enhancing algorithms for simulating potential environmental toxicants’ behavior in water, soil, and air environments. Tannia’s teaching experience includes a Leader Instructor at Brilliant Labs where she taught a range of digital topics, and a Digital Literacy Instructor for the Association for New Canadians.