Artificial intelligence publications
-
Efficient online learning and prediction of users’ desktop actions
We investigate prediction of users’ desktop activities in the Unix domain. We show that simple efficient many-class learning can perform well for action prediction, significantly improving over previously published results…
-
Prediction and Discovery of Users’ Desktop Behavior
In the first part of the paper, we show that efficient many-class learning can perform well for action prediction in the Unix domain, significantly improving over previously published results
-
What Were You Thinking? Filling in Missing Dataflow Through Inference in Learning from Demonstration
This paper addresses the problem of learning from demonstrations involving unobservable (e.g., mental) actions. We explore the use of knowledge base inference to complete missing dataflow and investigate the approach…
-
Changes to NIH Grant System May Backfire
Although we appreciate the many challenges facing the current NIH grant system and applaud attempts at reform, we believe that several of the changes planned will cause more harm than…
-
EcoCyc: a Comprehensive View of Escherichia Coli Biology
Recent EcoCyc developments include a new initiative to represent and curate all types of E. coli regulatory processes such as attenuation and regulation by small RNAs.
-
Efficient Message Passing and Propagation of Simple Temporal Constraints: Results on Semi-Structured Networks
We first show that for an STN, these messages can be represented compactly as sub-STNs. We then present an efficient message passing scheme for computing the minimal constraints of an…
-
Emma: An Event Management Assistant
In this extended abstract we describe the motivation, design, deployment and evaluation of the Emma system.
-
Logical Hierarchical Hidden Markov Models for Modeling User Activities
In this work we develop a representation that naturally combines the power of both relational and hierarchical models in the form of Logical Hierarchical Hidden Markov Models (LoHiHMMs).
-
MUESLI: Multiple utterance error correction for a spoken language interface
We propose a method for using all available information to help correct recognition errors in tasks that use constrained grammars of the kind used in the domain of Command and…
-
Annotation-Based Inference of Transporter Function
We present a method for inferring and constructing transport reactions for transporter proteins based primarily on the analysis of the names of individual proteins in the genome annotation of an…
-
Message from the Chairs
Presents the introductory welcome message from the conference proceedings of the 2008 IEEE International Conference on Computational Intelligence for Measurement Systems and Applications.
-
CALO Workflow Recognition and Proactive Assistance
This short video offers glimpses of how SRI's CALO agent helps users manage their tasks and time using advanced activity recognition algorithms based on logical probabilistic models.