Foundations and Methods 2

Knowledge

None

Description

This course offers two major components: an introduction to the mathematical and statistical methods required to apply data science and, in particular, neuronal network based machine learning approaches to problems and an introduction to human computer interaction, including cognitive, psychological and philosophical aspects, and interaction design.

Learning objectives

After successfully completing the course, students will be able to
Part 1: Data Analytics
•    Identify the key elements of the data analytics and machine learning lifecycle
•    Apply basic statistical tools and methods for analyzing data
•    Propose analytical methods for specific data domains
•    Explain the mathematical foundations of deep neu-ronal networks
•    Implement the standard training and evaluation pipe-lines used for modern machine learning models
•    Apply different evaluation and comparison metrics

Part 2: Human-Computer Interaction (HCI)
•    Design HCI experiments
•    Explain ethical and legal considerations
•    Evaluate experimental results
Describe at least two different methodological ap-proaches beyond the scientific experimental one

Comment

Content:

•    Cross-sectional review of relevant mathematical methods, from linear algebra to calculus
•    Descriptive statistics
•    Correlation and causation
•    Statistical modeling
•    Neuronal networks
•    Back propagation
•    Optimizers
•    Training, Testing, Evaluating
•    Convolution Models
•    Sequence Models
•    Generative Models
•    Selected model architectures
•    HCI Fundamentals
•    Experiment design
•    Ethical considerations
•    Legal considerations
•    Selected methods