# Introduction to Machine Learning and AI

## Code

IT-MAL1

## Version

3.0

## Offered by

ICT Engineering

## ECTS

5### Prerequisites

The course requires basic knowledge about algorithmic thinking, and in general a good understanding of mathematical concepts. Some programming experience is also presupposed but not strictly required. IT-DMA1 or similar.

### Main purpose

In this course, students will acquire both theoretical knowledge and practical skills in the application of machine learning methodologies to a spectrum of data types, encompassing both structured and unstructured datasets. The curriculum is designed to ensure that participants thoroughly understand and can adeptly utilize advanced tools and techniques essential for data preparation, preprocessing, and exploration. Students will be equipped to discern underlying structures and make informed predictions. Central to the course are four primary topics:

- Classification: Understanding and categorizing data into predefined classes.
- Regression: Predicting continuous outputs based on data input.
- Clustering: Identifying the inherent groupings within datasets.
- Dimensionality Reduction: Simplifying complex data structures without losing critical information.

### Knowledge

After having successfully completed the course, the student will have gained knowledge about algorithms, methods, techniques, tools, and applications within the following machine learning methods:

- Different data preparation and preprocessing methods
- Different types of classification algorithms, e.g., Naïve Bayes, k-Nearest Neighbor, Decision Trees, Logistic Regression, Support Vector Machines
- Different types of regression algorithms, e.g., simple linear regression, multiple linear regression, Ridge regression, Lasso regression
- Different types of dimensionality reduction algorithms, e.g. Principal component analyses, singular value decomposition, factor analysis
- Different types of clustering algorithms, e.g. k-Means clustering, Agglomerative clustering, DBSCAN
- Different metrics for assessing the strength and quality of their machine learning algorithms

### Skills

After successfully completing the course, the student will have developed the following skills:

- Ability to prepare and preprocess data for various machine learning applications effectively.
- Proficiency in implementing and tuning classification algorithms and selecting the appropriate classifier for a given dataset.
- Capability to apply regression techniques to predict continuous variables and evaluate the predictive ability of regression models.
- Using dimensionality reduction algorithms to interpret and simplify complex datasets.
- implementing clustering algorithms to categorize unlabelled datasets and determining the optimal number of clusters.
- Ability to use various machine learning tools and libraries
- Critical evaluation of model performance using various metrics and validation techniques.

### Competences

Upon completion of the course, students are expected to have acquired the competences to:

- Make informed decisions regarding the selection and application of machine learning techniques tailored to specific problem domains.
- Fine-tune and parametrize machine learning algorithms to optimize their performance on specific datasets.
- Conceptualize, design, and develop machine learning solutions for real-world problems.
- Articulate, communicate, and deliberate machine learning solutions, their implications, and associated decisions with both domain experts and non-technical persons.

### Topics

### Teaching methods and study activities

The mode of teaching will be classroom based and will involve lectures by the teacher and project work in class. There are a total of six small course assignments during the semester as well as one final group project. The total workload for the student is expected be around 125 hours.

### Resources

Hands-On Machine Learning with Scikit-Learn, Keras & TensorFlow by Aurélien Géron. 3rd edition, 2022.

Additional material will be uploaded to Itslearning.

### Evaluation

### Examination

Exam prerequisites:

At the end of the course, the student must upload a 1-page summary of each of their 6 assignments as well as a 2-page summary of their group project. The summaries must include a brief description of:

1) the assignment problem

2) how the assignment was solved, e.g., data acquisition, data preparation, feature engineering, feature extraction, etc.

3) the algorithms that were used to solve the problem.

4) the performance of the final model

5) a reflection of the learning outcome of solving the assignment.

Type of exam:

The exam is a 20-minute oral examination that departs from one of the six assignments that the student made during the semester.

The exam will also include an examination of the group project report.

The final grade will be based on an overall assessment of the six assignments, the group project report, and the oral examination.

Internal assessment.

Tools allowed:

N/A

Re-exam:

Same as the ordinary exam.

### Grading criteria

Grading according to the Danish 7-point scale.

### Additional information

### Responsible

Richard Brooks (rib)

### Valid from

01-02-2024 00:00:00

### Course type

7. semester

9. semester

Elective for the specialization Software

### Keywords

Classification, data mining, neural networks, regression, decision trees, algorithms, support vector machines, principal component analysis, clustering