Skip to content

philipfleischer/ML-AI

Repository files navigation

ML-AI (IN1160)

Introduction to Machine Learning and Artificial Intelligence at the University of Oslo (UiO). Course code: IN1160.

This repository contains my coursework, exercises, and obligatory assignments from IN1160, with a focus on practical machine learning, experimental methodology, reproducible notebooks, and responsible use of AI techniques using Python.

The assignments were mainly completed as Jupyter Notebooks (.ipynb). Some exported PDF versions included for documentation.


Course Overview

IN1160 provides a foundational introduction to machine learning (ML) and artificial intelligence (AI), with emphasis on practical applications, correct usage of existing ML methods, and design and evaluation of experiments.

The course covers:

  • Vector space representations
  • Text classification
  • k-nearest neighbors
  • Linear regression
  • Logistic regression
  • Neural networks
  • Decision trees and ensemble methods
  • Machine learning in practice
  • Reinforcement learning
  • Generative AI
  • Experimental design and evaluation
  • Ethical, philosophical, and historical perspectives on AI

Applications discussed include areas such as language technology, image processing, and robotics.


Project History

Obligatory Assignments (with full history)

Assignment Topic Browse Commit History
Oblig 1a Vector space representations Files Commits
Oblig 1b Supervised classification Files Commits
Oblig 2a Linear regression Files Commits
Oblig 2b Logistic regression Files Commits
Oblig 3a Decision trees & ML in practice Files Commits
Oblig 3b Reinforcement learning Files Commits

Learning Outcomes

After completing this course, I have gained:

  • Fundamental knowledge of practical ML methods and their applications
  • Experience using pre-implemented ML algorithms correctly and responsibly
  • Understanding of different data representations
  • Experience with vector spaces and similarity measures
  • Experience with classification, regression, clustering, and reinforcement learning
  • Ability to design, conduct, and evaluate ML-based experiments
  • Ability to assess strengths and weaknesses of different ML methods
  • Awareness of ethical, philosophical, and sustainability-related issues in AI
  • Knowledge of the historical development of AI and machine learning

Technologies and Tools

  • Python 3
  • Jupyter Notebook
  • NumPy
  • scikit-learn
  • Matplotlib / Seaborn (where applicable)

Author

Philip Elias Fleischer Bachelor’s student in Informatics: Programming and System Architecture University of Oslo (UiO)


About

Introduction course to Machine Learning and Artificial Intelligence at UIO, Course code: IN1160.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors