Search For:

Displaying 1-18 out of 18 total
From Robots to Reinforcement Learning
Found in: 2013 IEEE 25th International Conference on Tools with Artificial Intelligence (ICTAI)
By Tongchun Du,Michael T. Cox,Don Perlis,Jared Shamwell,Tim Oates
Issue Date:November 2013
pp. 540-545
In this paper, we review recent advances in Reinforcement Learning (RL) in light of potential applications to robotics, introduce the basic concepts of RL and Markov Decision Process (MDP), and compare different RL algorithms such as Q-learning, Temporal D...
 
Using Modified Multivariate Bag-of-Words Models to Classify Physiological Data
Found in: Data Mining Workshops, International Conference on
By Patricia Ordóñez,Tom Armstrong,Tim Oates,Jim Fackler
Issue Date:December 2011
pp. 534-539
In this paper we present two novel multivariate time series representations to classify physiological data of different lengths. The representations may be applied to any group of multivariate time series data that examine the state or health of an entity....
 
Improving the Discovery and Characterization of Hidden Variables by Regularizing the LO-net
Found in: Machine Learning and Applications, Fourth International Conference on
By Soumi Ray,Tim Oates
Issue Date:December 2011
pp. 442-447
This paper presents an extension of the regularized neural network architecture, called the LO-net. LO-net is a neural network architecture that can infer both the existence and values of hidden variables in streaming multivariate time series. The core ide...
 
Classification of Patients Using Novel Multivariate Time Series Representations of Physiological Data
Found in: Machine Learning and Applications, Fourth International Conference on
By Patricia Ordóñez,Tom Armstrong,Tim Oates,Jim Fackler
Issue Date:December 2011
pp. 172-179
In this paper we present two novel multivariate time series representations to classify physiological data of different lengths. The representations may be applied to any group of multivariate time series data that examine the state or health of an entity....
 
Managing Uncertainty in Text-to-Sketch Tracking Problems
Found in: Tools with Artificial Intelligence, IEEE International Conference on
By Matthew D. Schmill,Tim Oates
Issue Date:November 2011
pp. 430-437
Text-to-Sketch (T2S) is a class of problems in which geolocation is performed using natural language descriptions of a location or locations as input. This is a challenging problem due to the many sources of uncertainty inherent to the task: there is often...
 
An Architecture for Bootstrapping Lexical Semantics and Grammatical Structures
Found in: Web Intelligence and Intelligent Agent Technology, IEEE/WIC/ACM International Conference on
By Tom Armstrong,Tim Oates
Issue Date:August 2011
pp. 155-158
Computational approaches to language acquisition typically reduce the problem to one of either learning syntax, or learning a lexicon -- isolated tasks. These problem simplifications have led to disconnected solutions and algorithms with no expectation of ...
 
Discovering and Characterizing Hidden Variables in Streaming Multivariate Time Series
Found in: Machine Learning and Applications, Fourth International Conference on
By Soumi Ray, Tim Oates
Issue Date:December 2010
pp. 913-916
Time series data naturally arises in many domains, such as industrial process control, robotics, finance, medicine, climatology, and numerous others. In many cases variables known to be causally relevant cannot be measured directly or the existence of such...
 
Learning by Reading by Learning to Read
Found in: International Conference on Semantic Computing
By Sergei Nirenburg, Tim Oates, Jesse English
Issue Date:September 2007
pp. 694-701
Knowledge-based natural language processing systems learn by reading, i.e., they process texts to extract knowledge. The performance of these systems crucially depends on knowledge about the domain of language itself, such as lexicons and ontologies to gro...
 
Ensembles in adversarial classification for spam
Found in: Proceeding of the 18th ACM conference on Information and knowledge management (CIKM '09)
By Deepak Chinavle, Pranam Kolari, Tim Finin, Tim Oates
Issue Date:November 2009
pp. 2015-2018
The standard method for combating spam, either in email or on the web, is to train a classifier on manually labeled instances. As the spammers change their tactics, the performance of such classifiers tends to decrease over time. Gathering and labeling mor...
     
PERUSE: An Unsupervised Algorithm for Finding Recurrig Patterns in Time Series
Found in: Data Mining, IEEE International Conference on
By Tim Oates
Issue Date:December 2002
pp. 330
This paper describes PERUSE, an unsupervised algorithm for finding recurring patterns in time series. It was initially developed and tested with sensor data from a mobile robot, i.e. noisy, re-valued, multivariate time series with variable intervals betwee...
 
Motif discovery in spatial trajectories using grammar inference
Found in: Proceedings of the 22nd ACM international conference on Conference on information & knowledge management (CIKM '13)
By Crystal Chen, Jessica Lin, Susan Frankenstein, Arnold P. Boedihardjo, Sunil Gandhi, Tim Oates
Issue Date:October 2013
pp. 1465-1468
Spatial trajectory analysis is crucial to uncovering insights into the motives and nature of human behavior. In this work, we study the problem of discovering motifs in trajectories based on symbolically transformed representations and context free grammar...
     
Real-time path planning for a robotic arm
Found in: Proceedings of the 4th International Conference on PErvasive Technologies Related to Assistive Environments (PETRA '11)
By Jennifer Sleeman, Tim Oates, Kavita Krishnaswamy
Issue Date:May 2011
pp. 1-4
With robotics technology, services can be provided to care for individuals with disabilities. This paper describes an effort to improve path planning performance for a robotic arm, resulting in faster user response in real-time. For a robotic arm, particul...
     
Using latent semantic analysis to find different names for the same entity in free text
Found in: Proceedings of the fourth international workshop on Web information and data management (WIDM '02)
By Tim Oates, Vinay Bhat, Vishal Shanbhag
Issue Date:November 2002
pp. 31-35
A common problem faced when gathering information from the web is the use of different names to refer to the same entity. For example, the city in India referred to as Bombay in some documents may be referred to as Mumbai in others because its name officia...
     
Toward natural language interfaces for robotic agents: grounding linguistic meaning in sensors
Found in: Proceedings of the fourth international conference on Autonomous agents (AGENTS '00)
By Paul R. Cohen, Tim Oates, Zachary Eyler-Walker
Issue Date:June 2000
pp. 227-228
When creating virtual reality environments a large amount of the interaction needs to be programmed. The problem with this is that non-computer expert users lack the programming skills necessary to create useful applications. Specifying interactions remain...
     
Identifying qualitatively different outcomes of actions: gaining autonomy through learning
Found in: Proceedings of the fourth international conference on Autonomous agents (AGENTS '00)
By Matthew D. Schmill, Paul R. Cohen, Tim Oates
Issue Date:June 2000
pp. 110-111
When creating virtual reality environments a large amount of the interaction needs to be programmed. The problem with this is that non-computer expert users lack the programming skills necessary to create useful applications. Specifying interactions remain...
     
Identifying distinctive subsequences in multivariate time series by clustering
Found in: Proceedings of the fifth ACM SIGKDD international conference on Knowledge discovery and data mining (KDD '99)
By Tim Oates
Issue Date:August 1999
pp. 322-326
This talk is an interim report on the 5 year plan launched in 1996 to provide a theoretical and computational foundation of Statistics for massive data sets. The plan coincided with the formation of AT&T Labs and the proposed research agenda of the In...
     
Efficient progressive sampling
Found in: Proceedings of the fifth ACM SIGKDD international conference on Knowledge discovery and data mining (KDD '99)
By David Jensen, Foster Provost, Tim Oates
Issue Date:August 1999
pp. 23-32
This talk is an interim report on the 5 year plan launched in 1996 to provide a theoretical and computational foundation of Statistics for massive data sets. The plan coincided with the formation of AT&T Labs and the proposed research agenda of the In...
     
Neo: learning conceptual knowledge by sensorimotor interaction with an environment
Found in: Proceedings of the first international conference on Autonomous agents (AGENTS '97)
By Carole R. Beal, Marc S. Atkin, Paul R. Cohen, Tim Oates
Issue Date:February 1997
pp. 170-177
When creating virtual reality environments a large amount of the interaction needs to be programmed. The problem with this is that non-computer expert users lack the programming skills necessary to create useful applications. Specifying interactions remain...
     
 1