Open Access. Powered by Scholars. Published by Universities.®

Artificial Intelligence and Robotics Commons

Open Access. Powered by Scholars. Published by Universities.®

1,746 Full-Text Articles 2,265 Authors 544,330 Downloads 142 Institutions

All Articles in Artificial Intelligence and Robotics

Faceted Search

1,746 full-text articles. Page 65 of 67.

A First Practical Algorithm For High Levels Of Relational Consistency, Shant Karakashian, Robert J. Woodward, Christopher Reesons, Berthe Y. Choueiry, Christian Bessiere 2010 University of Nebraska-Lincoln

A First Practical Algorithm For High Levels Of Relational Consistency, Shant Karakashian, Robert J. Woodward, Christopher Reesons, Berthe Y. Choueiry, Christian Bessiere

CSE Conference and Workshop Papers

Consistency properties and algorithms for achieving them are at the heart of the success of Constraint Programming. In this paper, we study the relational consistency property R(∗,m)C, which is equivalent to m-wise consistency proposed in relational databases. We also define wR(∗,m)C, a weaker variant of this property. We propose an algorithm for enforcing these properties on a Constraint Satisfaction Problem by tightening the existing relations and without introducing new ones. We empirically show that wR(∗,m)C solves in a backtrack-free manner all the instances of some CSP benchmark classes, thus hinting at the tractability of ...


Generalized Crowding For Genetic Algorithms, Ole J. Mengshoel, Severino F. Galan 2010 Carnegie Mellon University

Generalized Crowding For Genetic Algorithms, Ole J. Mengshoel, Severino F. Galan

Ole J Mengshoel

Crowding is a technique used in genetic algorithms to preserve diversity in the population and to prevent premature convergence to local optima. It consists of pairing each offspring with a similar individual in the current population (pairing phase) and deciding which of the two will remain in the population (replacement phase). The present work focuses on the replacement phase of crowding, which usually has been carried out by one of the following three approaches: Deterministic, Probabilistic, and Simulated Annealing. These approaches present some limitations regarding the way replacement is conducted. On the one hand, the first two apply the same ...


Anytime Planning For Decentralized Pomdps Using Expectation Maximization, Akshat KUMAR, Shlomo ZILBERSTEIN 2010 Singapore Management University

Anytime Planning For Decentralized Pomdps Using Expectation Maximization, Akshat Kumar, Shlomo Zilberstein

Research Collection School Of Information Systems

Decentralized POMDPs provide an expressive framework for multi-agent sequential decision making. While finite-horizon DECPOMDPs have enjoyed signifcant success, progress remains slow for the infinite-horizon case mainly due to the inherent complexity of optimizing stochastic controllers representing agent policies. We present a promising new class of algorithms for the infinite-horizon case, which recasts the optimization problem as inference in a mixture of DBNs. An attractive feature of this approach is the straightforward adoption of existing inference techniques in DBNs for solving DEC-POMDPs and supporting richer representations such as factored or continuous states and actions. We also derive the Expectation Maximization (EM ...


Architecture Optimization, Training Convergence And Network Estimation Robustness Of A Fully Connected Recurrent Neural Network, Xiaoyu Wang 2010 Clemson University

Architecture Optimization, Training Convergence And Network Estimation Robustness Of A Fully Connected Recurrent Neural Network, Xiaoyu Wang

All Dissertations

Recurrent neural networks (RNN) have been rapidly developed in recent years. Applications of RNN can be found in system identification, optimization, image processing, pattern reorganization, classification, clustering, memory association, etc.
In this study, an optimized RNN is proposed to model nonlinear dynamical systems. A fully connected RNN is developed first which is modified from a fully forward connected neural network (FFCNN) by accommodating recurrent connections among its hidden neurons. In addition, a destructive structure optimization algorithm is applied and the extended Kalman filter (EKF) is adopted as a network's training algorithm. These two algorithms can seamlessly work together to ...


Handling Concept Drift In Text Data Stream Constrained By High Labelling Cost, Patrick Lindstrom, Sarah Jane Delany, Brian Mac Namee 2010 Dublin Institute of Technology

Handling Concept Drift In Text Data Stream Constrained By High Labelling Cost, Patrick Lindstrom, Sarah Jane Delany, Brian Mac Namee

Conference papers

In many real-world classification problems the concept being modelled is not static but rather changes over time - a situation known as concept drift. Most techniques for handling concept drift rely on the true classifications of test instances being available shortly after classification so that classifiers can be retrained to handle the drift. However, in applications where labelling instances with their true class has a high cost this is not reasonable. In this paper we present an approach for keeping a classifier up-to-date in a concept drift domain which is constrained by a high cost of labelling. We use an active ...


Towards Finding Robust Execution Strategies For Rcpsp/Max With Durational Uncertainty, Na FU, Pradeep VARAKANTHAM, Hoong Chuin LAU 2010 Singapore Management University

Towards Finding Robust Execution Strategies For Rcpsp/Max With Durational Uncertainty, Na Fu, Pradeep Varakantham, Hoong Chuin Lau

Research Collection School Of Information Systems

Resource Constrained Project Scheduling Problems with minimum and maximum time lags (RCPSP/max) have been studied extensively in the literature. However, the more realistic RCPSP/max problems — ones where durations of activities are not known with certainty – have received scant interest and hence are the main focus of the paper. Towards addressing the significant computational complexity involved in tackling RCPSP/max with durational uncertainty, we employ a local search mechanism to generate robust schedules. In this regard, we make two key contributions: (a) Introducing and studying the key properties of a new decision rule to specify start times of activities ...


Point-Based Backup For Decentralized Pompds: Complexity And New Algorithms, Akshat KUMAR, Shlomo ZILBERSTEIN 2010 Singapore Management University

Point-Based Backup For Decentralized Pompds: Complexity And New Algorithms, Akshat Kumar, Shlomo Zilberstein

Research Collection School Of Information Systems

Decentralized POMDPs provide an expressive framework for sequential multi-agent decision making. Despite their high complexity, there has been significant progress in scaling up existing algorithms, largely due to the use of point-based methods. Performing point-based backup is a fundamental operation in state-of-the-art algorithms. We show that even a single backup step in the multi-agent setting is NP-Complete. Despite this negative worst-case result, we present an efficient and scalable optimal algorithm as well as a principled approximation scheme. The optimal algorithm exploits recent advances in the weighted CSP literature to overcome the complexity of the backup operation. The polytime approximation scheme ...


Financial Time Series Forecasting With Machine Learning Techniques: A Survey, Bjoern Krollner, Bruce Vanstone, Gavin Finnie 2010 Bond University

Financial Time Series Forecasting With Machine Learning Techniques: A Survey, Bjoern Krollner, Bruce Vanstone, Gavin Finnie

Gavin Finnie

Stock index forecasting is vital for making informed investment decisions. This paper surveys recent literature in the domain of machine learning techniques and artificial intelligence used to forecast stock market movements. The publications are categorised according to the machine learning technique used, the forecasting timeframe, the input variables used, and the evaluation techniques employed. It is found that there is a consensus between researchers stressing the importance of stock index forecasting. Artificial Neural Networks (ANNs) are identified to be the dominant machine learning technique in this area. We conclude with possible future research directions.


Financial Time Series Forecasting With Machine Learning Techniques: A Survey, Bjoern Krollner, Bruce Vanstone, Gavin Finnie 2010 Bond University

Financial Time Series Forecasting With Machine Learning Techniques: A Survey, Bjoern Krollner, Bruce Vanstone, Gavin Finnie

Bjoern Krollner

Stock index forecasting is vital for making informed investment decisions. This paper surveys recent literature in the domain of machine learning techniques and artificial intelligence used to forecast stock market movements. The publications are categorised according to their research motivation, the machine learning technique used, the surveyed stock market, the forecasting time-frame, the input variables used, and the evaluation techniques employed. It is found that there is a consensus between researchers stressing the importance of stock index forecasting and that the results are promising. Artificial Neural Networks (ANNs) are identified to be the dominant machine learning technique in this area ...


Financial Time Series Forecasting With Machine Learning Techniques: A Survey, Bjoern Krollner, Bruce Vanstone, Gavin Finnie 2010 Bond University

Financial Time Series Forecasting With Machine Learning Techniques: A Survey, Bjoern Krollner, Bruce Vanstone, Gavin Finnie

Bruce Vanstone

Stock index forecasting is vital for making informed investment decisions. This paper surveys recent literature in the domain of machine learning techniques and artificial intelligence used to forecast stock market movements. The publications are categorised according to the machine learning technique used, the forecasting timeframe, the input variables used, and the evaluation techniques employed. It is found that there is a consensus between researchers stressing the importance of stock index forecasting. Artificial Neural Networks (ANNs) are identified to be the dominant machine learning technique in this area. We conclude with possible future research directions.


Graph-Based Weakly-Supervised Methods For Information Extraction & Integration, Partha P. Talukdar 2010 University of Pennsylvania

Graph-Based Weakly-Supervised Methods For Information Extraction & Integration, Partha P. Talukdar

Departmental Papers (CIS)

The variety and complexity of potentially-related data resources available for querying --- webpages, databases, data warehouses --- has been growing ever more rapidly. There is a growing need to pose integrative queries across multiple such sources, exploiting foreign keys and other means of interlinking data to merge information from diverse sources. This has traditionally been the focus of research within Information Extraction (IE) and Information Integration (II) communities, with IE focusing on converting unstructured sources into structured sources, and II focusing on providing a unified view of diverse structured data sources. However, most of the current IE and II methods, which can ...


Memristics: Memristors, Again? – Part Ii, How To Transform Wired ‘Translations’ Between Crossbars Into Interactions?, Rudolf Kaehr 2010 ThinkArt Lab Glasgow

Memristics: Memristors, Again? – Part Ii, How To Transform Wired ‘Translations’ Between Crossbars Into Interactions?, Rudolf Kaehr

Rudolf Kaehr

The idea behind this patchwork of conceptual interventions is to show the possibility of a “buffer-free” modeling of the crossbar architecture for memristive systems on the base of a purely difference-theoretical approach. It is considered that on a nano-electronic level principles of interpretation appears as mechanisms of complementarity. The most basic conceptual approach to such a complementarity is introduced as an interchangeability of operators and operands of an operation. Therefore, the architecture of crossbars gets an interpretation as complementarity between crossbar functionality and “buffering” translation functionality. That is, the same matter functions as operator and at once, as operand – and ...


Memristics: Memristors, Again?, Rudolf Kaehr 2010 ThinkArt Lab Glasgow

Memristics: Memristors, Again?, Rudolf Kaehr

Rudolf Kaehr

This collection gives first and short critical reflections on the concepts of memristics, memristors and memristive systems and the history of similar movements with an own focus on a possible interplay between memory and computing functions, at once, at the same place and time, to achieve a new kind of complementarity between computation and memory on a single chip without retarding buffering conditions.


Optimization And Analysis Of A Robotic Navigational Algorithm, Derek Carlson, Joshua Brown Kramer, Faculty Advisor 2010 Illinois Wesleyan University

Optimization And Analysis Of A Robotic Navigational Algorithm, Derek Carlson, Joshua Brown Kramer, Faculty Advisor

John Wesley Powell Student Research Conference

The problem of robot navigation involves planning a path to move a robot from a start point to a known target point within an obstacle course. The efficiency of such an algorithm can be measured in several ways. For instance, Lumelsky and Stepanov measure the length of the path taken in terms of obstacle perimeters. Gabriely and Rimon compare their two-dimensional algorithm's efficiency to that of the optimal algorithm. Brown Kramer and Sabalka expand upon the work of Gabriely and Rimon to produce an algorithm for dimensions greater than two. The primary objective of this research was to implement ...


Artificial Intelligence: Soon To Be The World’S Greatest Intelligence, Or Just A Wild Dream?, Edward R. Kollett 2010 Johnson & Wales University - Providence

Artificial Intelligence: Soon To Be The World’S Greatest Intelligence, Or Just A Wild Dream?, Edward R. Kollett

Academic Symposium of Undergraduate Scholarship

The purpose of the paper was to examine the field of artificial intelligence. In particular, the paper focused on what has been accomplished towards the goal of making a machine that can think like a human, and the hardships that researchers in the field has faced. It also touched upon the potential outcomes of success. Why is this paper important? As computers become more powerful, the common conception is that they are becoming more intelligent. As computers become more integrated with society and more connected with each other, people again believe they are becoming smarter. Therefore, it is important that ...


Autonomous Satellite Operations For Cubesat Satellites, Jason Lionel Anderson 2010 California Polytechnic State University - San Luis Obispo

Autonomous Satellite Operations For Cubesat Satellites, Jason Lionel Anderson

Master's Theses and Project Reports

In the world of educational satellites, student teams manually conduct operations daily, sending commands and collecting downlinked data. Educational satellites typically travel in a Low Earth Orbit allowing line of sight communication for approximately thirty minutes each day. This is manageable for student teams as the required manpower is minimal. The international Global Educational Network for Satellite Operations (GENSO), however, promises satellite contact upwards of sixteen hours per day by connecting earth stations all over the world through the Internet. This dramatic increase in satellite communication time is unreasonable for student teams to conduct manual operations and alternatives must be ...


Selective Recursive Kernel Learning For Online Identification Of Nonlinear Systems With Narx Form, Yi Liu, Haiqing Wang, Jiang Yu, Ping Li 2010 Zhejiang University

Selective Recursive Kernel Learning For Online Identification Of Nonlinear Systems With Narx Form, Yi Liu, Haiqing Wang, Jiang Yu, Ping Li

Dr. Yi Liu

Online identification of nonlinear systems is still an important while difficult task in practice. A general and simple online identification method, namely Selective Recursive Kernel Learning (SRKL), is proposed for multi-input–multi-output (MIMO) systems with the nonlinear autoregressive with exogenous input form. A two-stage RKL online identification framework is first formulated, where the information contained by a sample (i.e., the new arriving or old useless one) can be introduced into and/or deleted from the model, recursively. Then, a sparsification strategy to restrict the model complexity is developed to guarantee all the output channels of the MIMO model accurate ...


Designing Successful Online Courses - Part 2, Kathleen P. King 2010 University of South Florida

Designing Successful Online Courses - Part 2, Kathleen P. King

Leadership, Counseling, Adult, Career and Higher Education Faculty Publications

Once again, our major goal is to provide faculty with consistent guidance through the many instructional decisions and design steps they need to pursue in this process. This process is a fantastic opportunity to craft a virtual learning space in which people can engaging in learning beyond the constraints of time and space.


Designing Successful Online Courses - Part 2, Kathleen P. King 2010 University of South Florida

Designing Successful Online Courses - Part 2, Kathleen P. King

Kathleen P King

Once again, our major goal is to provide faculty with consistent guidance through the many instructional decisions and design steps they need to pursue in this process. This process is a fantastic opportunity to craft a virtual learning space in which people can engaging in learning beyond the constraints of time and space.


Five Strategies For Successful Writing Of Reports And Essays, Kathleen P. King 2010 University of South Florida

Five Strategies For Successful Writing Of Reports And Essays, Kathleen P. King

Leadership, Counseling, Adult, Career and Higher Education Faculty Publications

Many people cannot get started with their literary projects because they do not know where to start. In this brief article, I share insight from years of teaching students and professionals of all ages how to prepare professional work.


Digital Commons powered by bepress