Technical Workshop " Machine Learning with Python Part 3" By: Akram Vasighizaker

Thursday, March 7, 2024 - 13:00 to 14:00

The School of Computer Science...

Machine Learning with Python Part 3

Presenter:  Akram Vasighizaker

Date: Thursday, March 7th, 2024

Time: 1:00 pm – 2:00 pm

Location: 4th Floor (Workshop space) at 300 Ouellette Avenue (School of Computer Science Advanced Computing Hub)

 

Abstract: 

 This series of workshops focuses on Python programming specifically for machine learning tasks. We will start with an introduction to machine learning and Python commands, which are designed to implement machine learning algorithms such as classification tasks, in Jupyter Notebook on Google Colab. Finally, we will take a look at two other platforms, Microsoft Azure Machine Learning Studio and Weka, by performing a whole pipeline of a machine learning task. The code and data are available at Github: https://github.com/vasighiz/COMP8967-1-R-2022S-Internship-Project-I and participants can follow activities during the workshop.

 

Workshop Outline:

Introduction to Different Platforms for Machine Learning Task

  • Getting Started with Python for Machine Learning
  • Data Cleaning and Exploring in Python – Pandas
  • Machine Learning with Scikit-Learn
  • Multiclass classification in Scikit-learn (Case study: Decision Tree) 
  • Two-class Classification in Scikit-Learn (Case study: k-NN) 
  • Precision-Recall curve
  • Evaluation using cross-validation
  • Find the optimum value of parameters (hyperparameter tuning)
  • Predictions and Evaluations
  • Calculate and Visualize the Confusion Matrix
  • Learn the model and fit on data
  • Split data to train set and validation set
  • Normalizing and Feature scaling
  • Split data into features and label

Prerequisites:

Familiar with programming

Biography:

Akram is a Ph.D. in Computer Science and has been with the School of Computer Science since Jan 2020. She is an experienced data scientist with a passion for machine learning and data science pipelines in interdisciplinary fields. Her expertise is specifically in representation learning and Bioinformatics.