Author name cluster
Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.
IS Journal 2025 Journal Article
In this commemorative article, five past editors-in-chief of IEEE Intelligent Systems reflect on the magazine’s first 40 years and share their memories.
TMLR Journal 2024 Journal Article
With the proliferation of large pre-trained models in various domains, transfer learning has gained prominence where intermediate representations from these models can be leveraged to train better (target) task-specific models, with possibly limited labeled data. Although transfer learning can be beneficial in many applications, it can transfer undesirable information to target tasks that may severely curtail its performance in the target domain or raise ethical concerns related to privacy and/or fairness. In this paper, we propose a novel approach for suppressing the transfer of user-determined semantic concepts (viz. color, glasses, etc.) in intermediate source representations to target tasks without retraining the source model which can otherwise be expensive or even infeasible. Notably, we tackle a bigger challenge in the input data as a given intermediate source representation is biased towards the source task, thus possibly further entangling the desired concepts. We evaluate our approach qualitatively and quantitatively in the visual domain showcasing its efficacy for classification and generative source models. Finally, we provide a concept selection approach that automatically suppresses the undesirable concepts.
AAAI Conference 2019 Conference Paper
In many domains, collecting sufficient labeled training data for supervised machine learning requires easily accessible but noisy sources, such as crowdsourcing services or tagged Web data. Noisy labels occur frequently in data sets harvested via these means, sometimes resulting in entire classes of data on which learned classifiers generalize poorly. For real world applications, we argue that it can be beneficial to avoid training on such classes entirely. In this work, we aim to explore the classes in a given data set, and guide supervised training to spend time on a class proportional to its learnability. By focusing the training process, we aim to improve model generalization on classes with a strong signal. To that end, we develop an online algorithm that works in conjunction with classifier and training algorithm, iteratively selecting training data for the classifier based on how well it appears to generalize on each class. Testing our approach on a variety of data sets, we show our algorithm learns to focus on classes for which the model has low generalization error relative to strong baselines, yielding a classifier with good performance on learnable classes.
IS Journal 2017 Journal Article
The guest editors of this special issue on cognitive computing discuss the field in general and the four articles they selected to represent it in particular.
IS Journal 2017 Journal Article
With the AlphaGo computer program's recent win over one of the world's expert Go players, AI researchers need to explore new challenges in the game-playing arena. While there are a number of games to explore, the authors pose a true challenge for the next decade: attacking human-oriented games such as Dungeons & Dragons.
AAAI Conference 2014 Conference Paper
Predicting human activities is important for improving recommender systems or analyzing social relationships among users. Those human activities are usually represented as multi-object relationships (e. g. user’s tagging activities for items or user’s tweeting activities at some locations). Since multi-object relationships are naturally represented as a tensor, tensor factorization is becoming more important for predicting users’ possible activities. However, its prediction accuracy is weak for ambiguous and/or sparsely observed objects. Our solution, Semantic data Representation for Tensor Factorization (SRTF), tackles these problems by incorporating semantics into tensor factorization based on the following ideas: (1) It first links objects to vocabularies/taxonomies and resolves the ambiguity caused by objects that can be used for multiple purposes. (2) It next links objects to composite classes that merge classes in different kinds of vocabularies/taxonomies (e. g. classes in vocabularies for movie genres and those for directors) to avoid low prediction accuracy caused by rough-grained semantics. (3) It then lifts sparsely observed objects into their classes to solve the sparsity problem for rarely observed objects. To the best of our knowledge, this is the first study that leverages semantics to inject expert knowledge into tensor factorization. Experiments show that SRTF achieves up to 10% higher accuracy than state-of-the-art methods.
IS Journal 2012 Journal Article
This article discusses Data. gov, the world's largest open government, data-sharing website, and the use of linked data in some of the site's community pages.
IS Journal 2011 Journal Article
The Web is a critical global infrastructure. Since its emergence in the mid-1990s, it has exploded into hundreds of billions of pages that touch almost all aspects of modern life. Today the jobs of more and more people depend on the Web. Media, banking, and healthcare are being revolutionized by it, and governments are even considering how to run their countries with it.
IS Journal 2009 Journal Article
This special issue collects some of the best contributions to the first international Web Science Conference, exploring effects of the evolving Web on human society.
IS Journal 2009 Journal Article
Oliver G. Selfridge, a leader in early artificial intelligence research, whose work extended from 1956 to 2008, recently passed away. His research in machine learning, neural networks and agent-based computing still influence AI today. He helped organize the 1956 Dartmouth summer school, which is generally seen as the origin of American AI and developed Pandemonium, an early AI program that dealt with learning and reasoning, during his more than 50-year career.
IS Journal 2008 Journal Article
This special issue, rather than focusing on tools specifically for ontologies, looks at how they're being used and becoming part of the overall Web ecology. This article is part of a special issue called Semantic Web Update.
IS Journal 2008 Journal Article
The recipients of the 2008 IEEE Intelligent Systems 10 to Watch award—Philipp Cimiano, Dmitri Dolgov, Anat Levin, Peter Mika, Brian Milch, Louis-Philippe Morency, Boris Motik, Jennifer Neville, Erik Sudderth, and Luis von Ahn—discuss their current research and their visions of AI for the future.
IS Journal 2008 Journal Article
Is artificial intelligence headed for another AI Winter? Not if we take action now.
IS Journal 2008 Journal Article
Online scientific interaction outside the traditional journal space is becoming more and more important to academic communication.
IS Journal 2008 Journal Article
Despite all the major AI successes, when it comes to really understanding the human mind, we still know very little.
IS Journal 2008 Journal Article
Computer science research and technology can make a real difference in the world. The recent earthquake in China provides one example.
IS Journal 2007 Journal Article
Editor in Chief James Hendler comments on responses he received about his essay "Where Are All the Intelligent Agents? " in the May/June issue.
IS Journal 2007 Journal Article
This issue features a new department: Applications: Homeland Security. Picking the name was no easy matter.
IS Journal 2007 Journal Article
One possible model for scientific publishing is the overlay journal, which takes some interdisciplinary theme and provides links to papers published elsewhere. By providing links rather than republishing, the overlay journal provides a service to both the reader, by linking to many publications, and the publishers, by bringing more eyeballs to their sites.
IS Journal 2007 Journal Article
The nature of academic publishing is changing, and computer scientists need to lead the way.
IS Journal 2007 Journal Article
Many of the exciting and important things that are happening with the Semantic Web come from the Web side rather than the AI side. So, to many AI researchers, this part of the technology is unknown and is thus the "dark side" of the Semantic Web.
IS Journal 2007 Journal Article
There has been much research and talk about intelligent agents, but few real-world implementations.
IS Journal 2006 Journal Article
James Hendler looks back at his first two years as editor in chief.
IJCAI Conference 1997 Conference Paper
AAAI Conference 1996 Conference Paper
This paper compares three commitment strategies for HTN planning: (1) a strategy that delays variable bindings as much as possible; (2) a strategy in which no non-primitive task is expanded until all variable constraints are committed; and (3) a strategy that chooses between expansion and variable instantiation based on the number of branches that will be created in the search tree. Our results show that while there exist planning domains in which the first two strategies do well, the third does well over a broader range of planning domains.
AIJ Journal 1995 Journal Article
IJCAI Conference 1991 Conference Paper
NeurIPS Conference 1988 Conference Paper
One att·empt at explaining human inferencing is that of spread(cid: 173) ing activat, ion, particularly in the st. ructured connectionist para(cid: 173) digm. This has resulted in t. he building of systems with semanti(cid: 173) cally nameable nodes which perform inferencing by examining t. he pat, t. erns of activation spread. In this paper we demonst. rate t. hat simple structured network infert'ncing can be p(>rformed by passing art. iva. t. ion over the weights learned by a distributed alga(cid: 173) rit, hm. Thus, an account, is provided which explains a well(cid: 173) behaved rela t ionship bet. ween structured and distri butt'd conn('c(cid: 173) t. ionist. a. pproachrs.