Visualization for Artificial Intelligence

Recommended Prerequisites

Data Visualization

Teaching Methods

The unit includes theoretical lectures where the fundamental concepts, principles and techniques and there are presented and explained in detail.

Lectures of practical nature play the role of strengthening the connection between theoretic knowledge and its practical application. For that purpose the course promotes the development of projects that allow the application of the fundamental concepts and the development of the necessary competences for the development of visualizations solutions for application in artificial intelligence.

Learning Outcomes

This course presents and discusses advanced data visualization tools and techniques, focusing on the development of data visualization solutions for artificial intelligence. Exploratory data analysis will also be addressed. Moreover, state of the art interaction techniques will be discussed and implemented.

 

By the end of the course, the student will have theoretical knowledge and practical experience on the development of visualizations for artificial intelligence, being able to design, implement, test and validate solutions for real world scenarios that require Large-Scale Visualization.

 

Main competencies to be developed are:

–analysis and synthesis, problem solving

–critical thinking

-practical application of the theoretical knowledge; research

Secondary competences are:

–organizing and planning

–work in teams

–autonomous learning, creativity

Work Placement(s)

No

Syllabus

Introduction to Data Visualization: Data visualization and its role in AI

Data Visualization Fundamentals

•          The principles of effective visualization

•          Representing different data types

•          Perception and cognition

Interactive Visualization

•          Libraries and tools for visualization

•          Applications and interactive dashboards

•          Principles for user-centred design

Exploratory Data Analysis

•          Data analysis and statistical visualization techniques

Visualization for AI algorithms and models

•          Model interpretation and explainability through visualization

•          Visualization to understand ML models, trees, rule-based models, and deep learning models

•          Visualization of training and prediction processes

Visualization in Natural Language Processing

Visualization of Data and Features

•          Techniques for visualizing high-dimension data and dimensionality reduction

•          Visualizing feature selection and extraction

Ethics in Data Visualization

•          Bias and fairness in visual representation and data

•          Ethical implicat

Assessment Methods

Assessment
Exam: 20.0%
Project: 80.0%

Bibliography

Munzner, T.: Visualization Analysis and Design, 2014.

 

Ware, C.: Information Visualization: Perception for Design, 2nd ed., 2004.

 

Meirelles, I: Design for Information: An Introduction to the Histories, Theories, and Best Practices Behind Effective Information Visualizations. Rockport Publishers, 2013

 

Healy, K. (2018). Data visualization: a practical introduction. Princeton University Press.

 

Few, S. (2006). Information dashboard design: The effective visual communication of data. O'Reilly Media, Inc..