Official website of the course "Human-AI Interaction" (code 01UJUIU) offered to Ph.D. students at Politecnico di Torino in the academic year 2019/2020, taught by Luigi De Russis.
This page contains the archived version for the 2019/2020 edition of the course. Short link to the current edition: http://bit.ly/polito-hcai
Schedule
- 16/01/2020 h. 14:30-18:30, aula 29B
- 23/01/2020 h. 14:00-18:00, aula 1T
- 30/01/2020 h. 14:00-18:00, aula 1T
- 05/02/2020 h. 9:00-13:00, aula 2I
- 12/02/2020 h. 9:00-13:00, aula 1T
Students are encouraged to attend the classes with their laptops.
Course Topics
Artificial Intelligence (AI) has become increasingly present and integrated in our daily lives, with complex and often unpredictable solutions. This complexity and unpredictability make it difficult for users to understand, trust, and adopt such solutions with success. The course aims at introducing methodologies and techniques to design and build intelligent interactive systems that are usable and useful for all, also reflecting on the impact that AI applications have and will have on their users. A combination of lectures and workshop-style sessions will introduce students to different techniques for creating such intelligent systems across a few selected domains.
- Introduction to Human-AI Interaction
- Trade-offs in Human-AI Interaction
- Augmenting or replacing people?
- Direct manipulation or agents?
- Designing and evaluating human-centered AI systems
- Guidelines and methods
- Data, bias, and trust
- Case study on conversational agents and chatbots
- Hands-on sessions: design and prototyping
The course was inspired and partially follows the Human-AI Interaction class (Fall 2018 and 2019) at Carnegie Mellon University.
Material
- Introduction
- AI in the World: Journey Map
- Trade-offs in Human-AI Interaction (with panels)
- Designing AI+People Systems
- Design Workshop (introduction)
- Conversational Agents
- example with Dialogflow and Python: https://github.com/luigidr/dialogflow-weather
- Course Evaluation: questionnaire
Exam
The exam will consist in the evaluation of three exercises proposed and developed during the class hours.
A successfull completion of two out of three exercises is needed to pass the exam.
- Exercise 1: Reading Panel (to be prepared by 23/01/2020)
- Esercise 2: Design Worksheet (PPTX)
- Esercise 3: Prototyping a Conversational Agent