Videos
This page lists videos of research talks and other relevant video material for researchers in KR. You can suggest new videos to be added by filling out the corresponding form. New updates will be added to the website after validation (usually within one day).
Add video
Probabilistic Logic Programming with Beta-Distributed Random Variables (AAAI 2020) (submitted 2020-12-04)
Federico Cerutti
Keywords:
We enable aProbLog—a probabilistic logical programming approach—to reason in presence of uncertain probabilities represented as Beta-distributed random variables. We achieve the same performance of state-of-the-art algorithms for highly specified and engineered domains, while simultaneously we maintain the flexibility offered by aProbLog in handling complex relational domains. Our motivation is that faithfully capturing the distribution of probabilities is necessary to compute an expected utility for effective decision making under uncertainty: unfortunately, these probability distributions can be highly uncertain due to sparse data. To understand and accurately manipulate such probability distributions we need a well-defined theoretical framework that is provided by the Beta distribution, which specifies a distribution of probabilities representing all the possible values of a probability when the exact value is unknown.
probabilistic logic programming; uncertain probabilities
Learning and reasoning in complex coalition information environments: a critical analysis (FUSION 2018) (submitted 2020-12-04)
Federico Cerutti
Keywords:
In this paper we provide a critical analysis with met- rics that will inform guidelines for designing distributed systems for Collective Situational Understanding (CSU). CSU requires both collective insight—i.e., accurate and deep understanding of a situation derived from uncertain and often sparse data and collective foresight—i.e., the ability to predict what will happen in the future. When it comes to complex scenarios, the need for a distributed CSU naturally emerges, as a single monolithic approach not only is unfeasible: it is also undesirable. We therefore propose a principled, critical analysis of AI techniques that can support specific tasks for CSU to derive guidelines for designing distributed systems for CSU.
human-machine knowledge fusion
Supporting scientific enquiry with uncertain sources (FUSION 2018) (submitted 2020-12-04)
Federico Cerutti
Keywords:
In this paper we propose a computational method- ology for assessing the impact of trust associated to sources of information in scientific enquiry activities building upon recent proposals of an ontology for situational understanding and results in computational argumentation. Often trust in the source of information serves as a proxy for evaluating the quality of the information itself, especially in the cases of information overhead. We show how our computational methodology, composed of an ontology for representing uncertain information and sources, as well as an argumentative process of conjecture and refutation, support human analysts in scientific enquiry, as well as high- lighting issues that demand further investigation.
argumentation; scientific enquiry; intelligence analysis
DIGHUM Seminar Series: An AI and Computer Science Dilemma: Could I? Should I? (submitted 2020-11-30)
Barbara J. Grosz
Keywords:
This talk will describe Harvard’s Embedded EthiCS program, a novel approach to integrating ethics into computer science education that incorporates ethical reasoning throughout courses in the standard computer science curriculum. The talk will describe the goals of Embedded EthiCS, the way the program works, lessons learned and challenges to sustainable implementations of such a program across different types of academic institutions.
Digital Humanism; AI; Teaching
3 Principles for Creating Safer AI (submitted 2020-11-30)
Stuart Russell
Keywords:
How can we harness the power of superintelligent AI while also preventing the catastrophe of robotic takeover? As we move closer toward creating all-knowing machines, AI pioneer Stuart Russell is working on something a bit different: robots with uncertainty. Hear his vision for human-compatible AI that can solve problems using common sense, altruism and other human values.
Human-compatible AI; Digital Humanism
IBM Project Debater (submitted 2020-11-30)
IntelligenceSquared Debates
Keywords:
In partnership with IBM, Intelligence Squared U.S. is hosting a unique debate between a world-class champion debater and an AI system. IBM Project Debater is the first AI system designed to debate humans on complex topics using a combination of pioneering research developed by IBM researchers, including: data-driven speechwriting and delivery, listening comprehension, and modeling human dilemmas.
AI; Debates
From Explainable AI to Human-centered AI (submitted 2020-11-30)
Andreas Holzinge
Keywords:
Due to raising ethical, social and legal issues, future AI supported systems must be made transparent, re-traceable, thus human interpretable. Andreas’ aim is to explain why a machine decision has been reached, paving the way towards explainable AI and Causability, ultimately fostering ethical responsible machine learning.
Explainable AI; Human-centered AI
ARG-tech Director, BBC Project, Moral Maze & Abortion on Trial (submitted 2020-11-30)
Professor Chris Reed
Keywords:
Professor Chris Reed from the ARG-tech group at the University of Dundee gives an overview of the BBC project involving ARG-tech and the Radio 4 Moral Maze programme as well as the live BBC 2 debate, Abortion on Trial. He also talks about how the relationship with the BBC came about.
Argumentation; Moral Maze
Modelling Multivariate Ranking Functions with Min-Sum Networks (submitted 2020-10-05)
Xiaoting Shao, Arseny Skryagin, Zhongjie Yu, Tjitze Rienstra, Matthias Thimm and Kristian Kersting
Keywords:
ranking functions; probabilistic reasoning
We introduce min-sum networks (MSNs) for a compact representation of ranking functions for multiple variables.