Collaborative Artificial Intelligence
Traditionally, Artificial Intelligence (AI) applications are realized as “centralized” solutions, where a single entity, e.g., an organization, collects massive amounts of data from end users to provide a suite of AI-powered services. The ethical concerns such centralized AI solutions pose (e.g., fairness, accountability, transparency, and privacy) are increasingly evident.
This course introduces collaborative artificial intelligence, which facilitates interactions among intelligent agents, including humans and AI agents, to realize decentralized AI applications. The topics covered include:
- Co-active design of decentralized AI systems
- Negotiation among autonomous agents
- Agent communication and interaction protocols
- Agent coordination mechanisms
Coalition Formation 2 (a)
at Thu, Apr 15, 2021 10:14:05
For Coalition Formation 2 (a), describing either how the subspaces are generated or what the subspaces are is sufficient. You do not have to list the contents of each subspace.
Coactive Design 1
at Thu, Apr 15, 2021 10:00:00
For the MCQ on Interdependency Analysis (IA), choose the most appropriate answer. Note that the question is about IA in particular, nor coactive design as a whole.
Computational Social Choice 3 (a)
at Thu, Apr 15, 2021 09:56:54
You should demonstrate and motivate your answer for both plurality rule and Borda rule.
Negotiation 3 (a)
at Thu, Apr 15, 2021 09:40:05
In the Negotiation 3(a) question there is no restriction on the strategies used by the agents: multiple agents may be using the same strategy.