Daniel Weld | University of Washington (original) (raw)

Papers by Daniel Weld

CACM, 2019

Since Artificial Intelligence (AI) software uses techniques like deep lookahead search and stocha... more Since Artificial Intelligence (AI) software uses techniques like deep lookahead search and stochastic optimization of huge neural networks to fit mammoth datasets, it often results in complex behavior that is difficult for people to understand. Yet organizations are deploying AI algorithms in many mission-critical settings. To trust their behavior, we must make AI intelligible, either by using inherently interpretable models or by developing new methods for explaining and controlling otherwise overwhelmingly complex decisions using local approximation, vocabulary alignment, and interactive explanation. This paper argues that intelligibility is essential, surveys recent work on building such systems, and highlights key directions for research.

National Conference on Artificial Intelligence, 1994

International Conference on Management of Data, 2001

Proceedings of the 16th international conference on World Wide Web - WWW '07, 2007

Proceedings of the 20th annual ACM symposium on User interface software and technology - UIST '07, 2007

Proceeding of the twenty-sixth annual CHI conference on Human factors in computing systems - CHI '08, 2008

Page 1. Improving the Performance of Motor-Impaired Users with Automatically-Generated, Ability-B... more Page 1. Improving the Performance of Motor-Impaired Users with Automatically-Generated, Ability-Based Interfaces Krzysztof Z. Gajos Computer Science & Eng. University of Washington Seattle, WA 98195 USA kgajos@cs.washington.edu ...

Proceedings of the 9th international conference on Intelligent user interface - IUI '04, 2004

Proceedings of the 8th international conference on Intelligent user interfaces - IUI '03, 2003

Proceedings 17th International Conference on Data Engineering, 2001

Proceedings of the 4th international conference on Intelligent user interfaces - IUI '99, 1999

Although Programming by Demonstration (PBD) hasthe potential to improve the productivity of unsop... more Although Programming by Demonstration (PBD) hasthe potential to improve the productivity of unsophisticatedusers, previous PBD systems have used brittle,heuristic, domain-specific approaches to execution-tracegeneralization. In this paper we define two applicationindependentmethods for performing generalization thatare based on well-understood machine learning technology. TGen vs uses version-space generalization, andTGen foil is based on the FOIL inductive logic programming algorithm. ...

International Joint Conference on Artificial Intelligence, 2001

Visitors who browse the web from wireless PDAs, cell phones, and pagers are frequently stymied by... more Visitors who browse the web from wireless PDAs, cell phones, and pagers are frequently stymied by web interfaces optimized for desktop PCs. Simply replacing graphics with text and reformatting ta- bles does not solve the problem, because deep link structures can still require minutes to traverse. In this paper we develop an algorithm, MINPATH, that automatically improves wireless web naviga-

International Joint Conference on Artificial Intelligence, 2003

Intelligent agents must function in an uncertain world, containing multiple objects and relations... more Intelligent agents must function in an uncertain world, containing multiple objects and relations that change over time. Unfortunately, no representation is currently available that can handle all these issues, while allowing for principled and efficient inference. This paper ad- dresses this need by introducing dynamic probabilistic relational models (DPRMs). DPRMs are an extension of dynamic Bayesian networks (DBNs) where each

International Joint Conference on Artificial Intelligence, 2001

The fastest growing community of web users is that of mobile visitors who browse with wireless PD... more The fastest growing community of web users is that of mobile visitors who browse with wireless PDAs, cell phones, and pagers. Unfortunately, most web sites today are optimized exclusively for desktop, broadband clients, and deliver content poorly suited for mobile devices — devices that can display only a few lines of text using slow wireless networks. To best serve the

International Conference on Machine Learning, 2000

Machine learning research has been very successful at producing powerful, broadly- applicable cla... more Machine learning research has been very successful at producing powerful, broadly- applicable classification learners. However, many practical learning problems do not fit the classification framework well, and as a re- sult the initial phase of suitably formulating the problem and incorporating the relevant domain knowledge can be very difficult and time-consuming. Here we propose a frame- work to systematize and

International Joint Conference on Artificial Intelligence, 1997

Page 1. Wrapper Induction for Information Extraction by Nicholas Kushmerick A dissertation submit... more Page 1. Wrapper Induction for Information Extraction by Nicholas Kushmerick A dissertation submitted in partial ful llment ... Abstract Wrapper Induction for Information Extraction by Nicholas Kushmerick Chairperson of Supervisory Committee: Professor Daniel S. Weld ...

Principles of Knowledge Representation and Reasoning, 1994

Closed world reasoning is the process of inferring thata logical sentence is false based on its a... more Closed world reasoning is the process of inferring thata logical sentence is false based on its absence froma knowledge base, or the inability to derive it. Previouswork on circumscription, autoepistemic logic,and database theory has explored logical axiomatizationsof closed world reasoning, and investigatedcomputational tractability for propositional theories.Work in planning has traditionally made the closedworld assumption but has avoided closed world reasoning.We

Proceedings of the 18th annual ACM symposium on User interface software and technology - UIST '05, 2005

Proceedings of the 6th international conference on Intelligent user interfaces - IUI '01, 2001

Proceedings of the eighth ACM SIGKDD international conference on Knowledge discovery and data mining - KDD '02, 2002

Proceedings of the tenth international conference on World Wide Web - WWW '01, 2001

Page 1. Personalizing Web Sites for Mobile Users Corin R. Anderson University of Washington Seatt... more Page 1. Personalizing Web Sites for Mobile Users Corin R. Anderson University of Washington Seattle, WA, USA corin@cs. washington.edu Pedro Domingos University of Washington Seattle, WA, USA pedrod@cs. washington.edu ...