Kagal, Lalana


Explaining Explanations: An Approach to Evaluating Interpretability of Machine Learning

arXiv.org Machine Learning

There has recently been a surge of work in explanatory artificial intelligence (XAI). This research area tackles the important problem that complex machines and algorithms often cannot provide insights into their behavior and thought processes. XAI allows users and parts of the internal system to be more transparent, providing explanations of their decisions in some level of detail. These explanations are important to ensure algorithmic fairness, identify potential bias/problems in the training data, and to ensure that the algorithms perform as expected. However, explanations produced by these systems is neither standardized nor systematically assessed. In an effort to create best practices and identify open challenges, we provide our definition of explainability and show how it can be used to classify existing literature. We discuss why current approaches to explanatory methods especially for deep neural networks are insufficient. Finally, based on our survey, we conclude with suggested future research directions for explanatory artificial intelligence.


Reports on the 2015 AAAI Spring Symposium Series

AI Magazine

The AAAI 2015 Spring Symposium Series was held Monday through Wednesday, March 23-25, at Stanford University near Palo Alto, California. The titles of the seven symposia were Ambient Intelligence for Health and Cognitive Enhancement, Applied Computational Game Theory, Foundations of Autonomy and Its (Cyber) Threats: From Individuals to Interdependence, Knowledge Representation and Reasoning: Integrating Symbolic and Neural Approaches, Logical Formalizations of Commonsense Reasoning, Socio-Technical Behavior Mining: From Data to Decisions, Structured Data for Humanitarian Technologies: Perfect Fit or Overkill?


Reports on the 2015 AAAI Spring Symposium Series

AI Magazine

The AAAI 2015 Spring Symposium Series was held Monday through Wednesday, March 23-25, at Stanford University near Palo Alto, California. The titles of the seven symposia were Ambient Intelligence for Health and Cognitive Enhancement, Applied Computational Game Theory, Foundations of Autonomy and Its (Cyber) Threats: From Individuals to Interdependence, Knowledge Representation and Reasoning: Integrating Symbolic and Neural Approaches, Logical Formalizations of Commonsense Reasoning, Socio-Technical Behavior Mining: From Data to Decisions, Structured Data for Humanitarian Technologies: Perfect Fit or Overkill? and Turn-Taking and Coordination in Human-Machine Interaction.The highlights of each symposium are presented in this report.


Reports of the AAAI 2011 Fall Symposia

AI Magazine

The Association for the Advancement of Artificial Intelligence was pleased to present the 2011 Fall Symposium Series, held Friday through Sunday, November 4–6, at the Westin Arlington Gateway in Arlington, Virginia. The titles of the seven symposia are as follows: (1) Advances in Cognitive Systems; (2) Building Representations of Common Ground with Intelligent Agents; (3) Complex Adaptive Systems: Energy, Information and Intelligence; (4) Multiagent Coordination under Uncertainty; (5) Open Government Knowledge: AI Opportunities and Challenges; (6) Question Generation; and (7) Robot-Human Teamwork in Dynamic Adverse Environment. The highlights of each symposium are presented in this report.


Reports of the AAAI 2011 Fall Symposia

AI Magazine

The Association for the Advancement of Artificial Intelligence was pleased to present the 2011 Fall Symposium Series, held Friday through Sunday, November 4–6, at the Westin Arlington Gateway in Arlington, Virginia. The titles of the seven symposia are as follows: (1) Advances in Cognitive Systems; (2) Building Representations of Common Ground with Intelligent Agents; (3) Complex Adaptive Systems: Energy, Information and Intelligence; (4) Multiagent Coordination under Uncertainty; (5) Open Government Knowledge: AI Opportunities and Challenges; (6) Question Generation; and (7) Robot-Human Teamwork in Dynamic Adverse Environment. The highlights of each symposium are presented in this report.


The Fractal Nature of the Semantic Web

AI Magazine

In the past, many knowledge representation systems failed because they were too monolithic and didn't scale well, whereas other systems failed to have an impact because they were small and isolated. Along with this trade-off in size, there is also a constant tension between the cost involved in building a larger community that can interoperate through common terms and the cost of the lack of interoperability. Its main contribution is in recognizing and supporting the fractal patterns of scalable web systems. In this article we discuss why fractal patterns are an appropriate model for web systems and how semantic web technologies can be used to design scalable and interoperable systems.


The Fractal Nature of the Semantic Web

AI Magazine

In the past, many knowledge representation systems failed because they were too monolithic and didn’t scale well, whereas other systems failed to have an impact because they were small and isolated. Along with this trade-off in size, there is also a constant tension between the cost involved in building a larger community that can interoperate through common terms and the cost of the lack of interoperability. The semantic web offers a good compromise between these approaches as it achieves wide-scale communication and interoperability using finite effort and cost. The semantic web is a set of standards for knowledge representation and exchange that is aimed at providing interoperability across applications and organizations. We believe that the gathering success of this technology is not derived from the particular choice of syntax or of logic. Its main contribution is in recognizing and supporting the fractal patterns of scalable web systems. These systems will be composed of many overlapping communities of all sizes, ranging from one individual to the entire population that have internal (but not global) consistency. The information in these systems, including documents and messages, will contain some terms that are understood and accepted globally, some that are understood within certain communities, and some that are understood locally within the system. The amount of interoperability between interacting agents (software or human) will depend on how many communities they have in common and how many ontologies (groups of consistent and related terms) they share. In this article we discuss why fractal patterns are an appropriate model for web systems and how semantic web technologies can be used to design scalable and interoperable systems.