Multi Label Classification in Machine Learning

1. Basic Python Programming

Variables, loops, functions, and data structures
Using libraries like NumPy, Pandas, and Matplotlib

2. Fundamentals of Machine Learning

Understanding:
- Supervised vs. unsupervised learning
- Classification vs. regression
- Overfitting and underfitting
Familiarity with Scikit-learn and basic ML pipelines

3. Understanding of Classification Algorithms

Logistic Regression
Decision Trees
Random Forest
Support Vector Machines (SVM)
K-Nearest Neighbors (KNN)

4. Basic Linear Algebra & Probability

Vectors, matrices, dot product
Probability distributions and conditional probability

5. Familiarity with Model Evaluation Metrics

Accuracy, precision, recall, F1-score
Especially:
- Micro vs. macro averaging
- ROC-AUC curves
- Confusion matrix

6. Basic Knowledge of Data Preprocessing

Handling missing data
Encoding categorical variables
Feature scaling (StandardScaler, MinMaxScaler)

7. Intro to Multi-Class vs Multi-Label Classification

Understand the difference between:
- Multi-class (one label per sample)
- Multi-label (multiple labels per sample)

This concept is core to the course, so prior awareness helps.

🧠 Bonus Skills (Nice to Have)

Jupyter Notebooks or Google Colab for interactive coding
Familiarity with deep learning frameworks (e.g., TensorFlow or PyTorch) if neural networks are involved
Some exposure to NLP or image classification, where multi-label problems are common

Course Content

What is Multi Label Classification in Machine Learning?

What Output Function to use in Multi Label Classification?

Multi Label Classification and Ground Truth Vector

Multi Label Classification and Loss Function

Multi Label Classification and Forward Pass

Multi Label Classification and Backpropagation of Gradients

A Dataset for Multi Label Classification

Exploring a Multi Label Classification Dataset using Python

Multi Label Classification: Customized Pytorch Dataset

Multi Label Classification: Dataloaders in Pytorch

Multi Label Classification in Machine Learning – Split into Training, Validation, Test Sets

Multi Label Classification in Machine Learning: How to Build a ResNet18 Model

How to Train a Multi Label classification Model?

How to Validate a Multi Label Classification Model?

About Instructor

Mehran

Dr. Mehran H. Bazargani is a researcher and educator specialising in machine learning and computational neuroscience. He earned his Ph.D. from University College Dublin, where his research centered on semi-supervised anomaly detection through the application of One-Class Radial Basis Function (RBF) Networks. His academic foundation was laid with a Bachelor of Science degree in Information Technology, followed by a Master of Science in Computer Engineering from Eastern Mediterranean University, where he focused on molecular communication facilitated by relay nodes in nano wireless sensor networks. Dr. Bazargani’s research interests are situated at the intersection of artificial intelligence and neuroscience, with an emphasis on developing brain-inspired artificial neural networks grounded in the Free Energy Principle. His work aims to model human cognition, including perception, decision-making, and planning, by integrating advanced concepts such as predictive coding and active inference. As a NeuroInsight Marie Skłodowska-Curie Fellow, Dr. Bazargani is currently investigating the mechanisms underlying hallucinations, conceptualising them as instances of false inference about the environment. His research seeks to address this phenomenon in neuropsychiatric disorders by employing brain-inspired AI models, notably predictive coding (PC) networks, to simulate hallucinatory experiences in human perception.

5 Courses