Open Access. Powered by Scholars. Published by Universities.®
Artificial Intelligence and Robotics Commons™
Open Access. Powered by Scholars. Published by Universities.®
- Discipline
-
- Engineering (46)
- Databases and Information Systems (29)
- Graphics and Human Computer Interfaces (23)
- Computer Engineering (21)
- Social and Behavioral Sciences (21)
-
- Medicine and Health Sciences (19)
- Software Engineering (18)
- Theory and Algorithms (18)
- Numerical Analysis and Scientific Computing (17)
- Other Computer Sciences (15)
- Operations Research, Systems Engineering and Industrial Engineering (13)
- Psychiatry and Psychology (13)
- Electrical and Computer Engineering (12)
- Psychological Phenomena and Processes (12)
- Behavior and Behavior Mechanisms (11)
- Information Security (10)
- Public Affairs, Public Policy and Public Administration (10)
- Transportation (9)
- Business (8)
- Robotics (7)
- Life Sciences (6)
- OS and Networks (6)
- Technology and Innovation (6)
- Applied Mathematics (4)
- Arts and Humanities (4)
- Environmental Monitoring (4)
- Environmental Sciences (4)
- Institution
-
- Singapore Management University (59)
- San Jose State University (23)
- Technological University Dublin (22)
- City University of New York (CUNY) (9)
- Missouri University of Science and Technology (5)
-
- Old Dominion University (5)
- Fordham University (4)
- Gettysburg College (4)
- LSU New Orleans (4)
- University of Nebraska - Lincoln (4)
- Vocational Training Council (4)
- California Polytechnic State University, San Luis Obispo (3)
- University of Louisville (3)
- University of Nebraska at Omaha (3)
- University of New Mexico (3)
- University of South Florida (3)
- Western University (3)
- Ateneo de Manila University (2)
- Bryn Mawr College (2)
- California State University, San Bernardino (2)
- Illinois State University (2)
- Louisiana State University (2)
- Munster Technological University (2)
- Purdue University (2)
- University of Montana (2)
- University of North Florida (2)
- University of Texas at El Paso (2)
- Utah State University (2)
- Air Force Institute of Technology (1)
- Antioch University (1)
- Keyword
-
- Machine learning (18)
- Artificial intelligence (16)
- Artificial Intelligence (14)
- Deep learning (11)
- Machine Learning (10)
-
- Robotics (7)
- Mental workload (6)
- Neural networks (5)
- Classification (4)
- Clustering (4)
- Deep Learning (4)
- Optimization (4)
- Reinforcement learning (4)
- AI (3)
- Behavior-Based (3)
- Computer vision (3)
- Deep neural networks (3)
- Formal Verification (3)
- Image segmentation (3)
- Neural Network (3)
- Semantics (3)
- Servers (3)
- Validation (3)
- Video games (3)
- Workload (3)
- Academic -- UNF -- Master of Science in Computer and Information Sciences; Dissertations (2)
- Activity Recognition (2)
- Artificial Neural Network (2)
- Automation (2)
- Bench-mark problems (2)
- Publication
-
- Research Collection School Of Computing and Information Systems (56)
- Master's Projects (23)
- H-Workload 2017: Models and Applications (Works in Progress) (15)
- Conference papers (7)
- Dissertations, Theses, and Capstone Projects (4)
-
- Electronic Theses and Dissertations (4)
- Faculty Publications (4)
- LSU New Orleans Theses and Dissertations (4)
- SIGNED: The Magazine of The Hong Kong Design Institute (4)
- Computer Science Faculty Publications (3)
- Publications and Research (3)
- Theses (3)
- UNO Student Research and Creative Activity Fair (3)
- USF Tampa Graduate Theses and Dissertations (3)
- Annual Symposium on Biomathematics and Ecology Education and Research (2)
- Computer Science ETDs (2)
- Computer Science Faculty Research and Scholarship (2)
- Doctoral Dissertations (2)
- Electrical and Computer Engineering Faculty Research & Creative Works (2)
- Electrical and Computer Engineering Publications (2)
- Graduate Student Theses, Dissertations, & Professional Papers (2)
- Masters Theses (2)
- Open Access Theses & Dissertations (2)
- School of Computing: Dissertations, Theses, and Student Research (2)
- Theses and Dissertations (2)
- UNF Graduate Theses and Dissertations (2)
- All Graduate Plan B and other Reports, Spring 1920 to Spring 2023 (1)
- All Graduate Theses and Dissertations, Spring 1920 to Summer 2023 (1)
- Angelo King Institute for Economic and Business Studies (AKI) (1)
- Annual ADFSL Conference on Digital Forensics, Security and Law (1)
- Publication Type
- File Type
Articles 121 - 150 of 211
Full-Text Articles in Artificial Intelligence and Robotics
Impact Of Artificial Intelligence, Robotics, And Machine Learning On Sales And Marketing, Keng Siau, Y. Yang
Impact Of Artificial Intelligence, Robotics, And Machine Learning On Sales And Marketing, Keng Siau, Y. Yang
Research Collection School Of Computing and Information Systems
AI, robotics, and machine learning are impacting the field of sales and marketing in an unprecedented way. A perfect storm is brewing! On one hand, online retail stores like Amazon are crushing the bricks and mortar stores. Sales and marketing professionals in bricks and mortar stores are facing a grim future. On the other hand, AI, robotics, and machine learning are replacing sales and marketing professionals in online stores. In fact, salespersons and marketers are predicted to be among the first to be replaced by robots. In a face-to-face environment, human may still prefer to interact with another human. In …
Lexicons In Sentiment Analytics, B. Yuan, Keng Siau
Lexicons In Sentiment Analytics, B. Yuan, Keng Siau
Research Collection School Of Computing and Information Systems
With the increasing amount of text data, sentiment analytics (SA) is becoming an important tool for text miners. An automated approach is needed to parse the online reviews and comments, and analyze their sentiments. Since lexicon is the most important component in SA, enhancing the quality of lexicons will improve the efficiency and accuracy of sentiment analysis. In this research, we study the effect of coupling a general lexicon with a specialized lexicon (for a specific domain) and its impact on sentiment analysis. Two special domains and one general domain were used. The two special domains are the petroleum domain …
Machine Learning Approaches To Sentiment Analytics, W. Zhao, Keng Siau
Machine Learning Approaches To Sentiment Analytics, W. Zhao, Keng Siau
Research Collection School Of Computing and Information Systems
One key aspect of sentiment analytics is emotion classification. This research studies the use of machine learning approaches to classify human emotion. Two different machine learning approaches were compared in an experimental study. In one approach, emotions from both genders were used to train the machine. In another approach, genders were separated and two separate machines were used to learn the emotions of the two genders. We also manipulated the training sample sizes and study the effect of training sample sizes on the two machine learning approaches. Our preliminary results show that the approach where the genders were separated produces …
Follow-My-Lead: Intuitive Indoor Path Creation And Navigation Using See-Through Interactive Videos, Quentin Roy, Simon T. Perrault, Shengdong Zhao, Richard Davis, Anuroop Pattena Vaniyar, Velko Vechev, Youngki Lee, Archan Misra
Follow-My-Lead: Intuitive Indoor Path Creation And Navigation Using See-Through Interactive Videos, Quentin Roy, Simon T. Perrault, Shengdong Zhao, Richard Davis, Anuroop Pattena Vaniyar, Velko Vechev, Youngki Lee, Archan Misra
Research Collection School Of Computing and Information Systems
We present Follow-My-Lead, an alternative indoor navigation technique that uses visual information recorded on an actual navigation path as a navigational guide. Its design revealed a trade-off between the fidelity of information provided to users and their effort to acquire it. Our first experiment revealed that scrolling through a continuous image stream of the navigation path is highly informative, but it becomes tedious with constant use. Discrete image checkpoints require less effort, but can be confusing. A balance may be struck by adding fast video transitions between image checkpoints, but precise control is required to handle difficult situations. Authoring still …
A Multi-Agent System For Coordinating Vessel Traffic, Teck-Hou Teng, Hoong Chuin Lau, Akshat Kumar
A Multi-Agent System For Coordinating Vessel Traffic, Teck-Hou Teng, Hoong Chuin Lau, Akshat Kumar
Research Collection School Of Computing and Information Systems
Environmental, regulatory and resource constraints affects the safety and efficiency of vessels navigating in and out of the ports. Movement of vessels under such constraints must be coordinated for improving safety and efficiency. Thus, we frame the vessel coordination problem as a multi-agent path-finding (MAPF) problem. We solve this MAPF problem using a Coordinated Path-Finding (CPF) algorithm. Based on the local search paradigm, the CPF algorithm improves on the aggregated path quality of the vessels iteratively. Outputs of the CPF algorithm are the coordinated trajectories. The Vessel Coordination Module (VCM) described here is the module encapsulating our MAPF-based approach for …
Real-Time Prediction Of Length Of Stay Using Passive Wi-Fi Sensing, Truc Viet Le, Baoyang Song, Laura Wynter
Real-Time Prediction Of Length Of Stay Using Passive Wi-Fi Sensing, Truc Viet Le, Baoyang Song, Laura Wynter
Research Collection School Of Computing and Information Systems
The proliferation of wireless technologies in today's everyday life is one of the key drivers of the Internet of Things (IoT). In addition to being an enabler of connectivity, the vast penetration of wireless devices today gives rise to a secondary functionality as a means of tracking and localization of the devices themselves. Indeed, in order to discover and automatically connect to known Wi-Fi networks, mobile devices have to scan and broadcast the so-called probe requests on all available channels, which can be captured and analyzed in a non-intrusive manner. Thus, one of the key applications of this feature is …
Real-Time Prediction Of Length Of Stay Using Passive Wi-Fi Sensing, Truc Viet Le, Baoyang Song, Laura Wynter
Real-Time Prediction Of Length Of Stay Using Passive Wi-Fi Sensing, Truc Viet Le, Baoyang Song, Laura Wynter
Research Collection School Of Computing and Information Systems
The proliferation of wireless technologies in today's everyday life is one of the key drivers of the Internet of Things (IoT). In addition to being an enabler of connectivity, the vast penetration of wireless devices today gives rise to a secondary functionality as a means of tracking and localization of the devices themselves. Indeed, in order to discover and automatically connect to known Wi-Fi networks, mobile devices have to scan and broadcast the so-called probe requests on all available channels, which can be captured and analyzed in a non-intrusive manner. Thus, one of the key applications of this feature is …
Stop Nuclear Smuggling Through Efficient Container Inspection, Xinrun Wang, Qingyu Guo, Bo An
Stop Nuclear Smuggling Through Efficient Container Inspection, Xinrun Wang, Qingyu Guo, Bo An
Research Collection School Of Computing and Information Systems
Since 2003, the U.S. government has spent $850 million on the Megaport Initiative which aims at stopping the nuclear smuggling in international container shipping through advanced inspection facilities including Non-Intrusive Inspection (NII) and Mobile Radiation Detection and Identification System (MRDIS). Unfortunately, it remains a significant challenge to efficiently inspect more than 11.7 million containers imported to the U.S. due to the limited inspection resources. Moreover, existing work in container inspection neglects the sophisticated behavior of the smuggler who can surveil the inspector’s strategy and decide the optimal (sequential) smuggling plan. This paper is the first to tackle this challenging container …
Towards Distributed Machine Learning In Shared Clusters: A Dynamically-Partitioned Approach, Peng Sun, Yonggang Wen, Nguyen Binh Duong Ta, Shengen Yan
Towards Distributed Machine Learning In Shared Clusters: A Dynamically-Partitioned Approach, Peng Sun, Yonggang Wen, Nguyen Binh Duong Ta, Shengen Yan
Research Collection School Of Computing and Information Systems
Many cluster management systems (CMSs) have been proposed to share a single cluster with multiple distributed computing systems. However, none of the existing approaches can handle distributed machine learning (ML) workloads given the following criteria: high resource utilization, fair resource allocation and low sharing overhead. To solve this problem, we propose a new CMS named Dorm, incorporating a dynamicallypartitioned cluster management mechanism and an utilizationfairness optimizer. Specifically, Dorm uses the container-based virtualization technique to partition a cluster, runs one application per partition, and can dynamically resize each partition at application runtime for resource efficiency and fairness. Each application directly launches …
A Parallelized Method For Solving Large Scale Integer Linear Optimization Problems Using Cut-And-Solve With Applications To Cgwas, John Brandenburg
A Parallelized Method For Solving Large Scale Integer Linear Optimization Problems Using Cut-And-Solve With Applications To Cgwas, John Brandenburg
Theses
The commercial solver CPLEX has been one of the top solvers of mixed-integer and purely integer linear problems for some time. Its method of solving, Branch-and-Cut, has been shown to be highly effective, but has its limits in terms of input sizes which are tractable, and cannot be effectively parallelized beyond a small number. Here we present a different method of solution, Cut-and-Solve, which utilizes the power of CPLEX to effectively parallelize any mixed-integer or integer linear problem. We have utilized Cut-and-Solve in a novel way to offer optimal solution guarantees more quickly. We will show comparisons of Cut-and-Solve to …
Granting Personhood For Sentient Non-Human Animals And Sentient Artificial Intelligences: A Demonstrative Argument, Jeremiah Meadows
Granting Personhood For Sentient Non-Human Animals And Sentient Artificial Intelligences: A Demonstrative Argument, Jeremiah Meadows
Virginias Collegiate Honors Council Conference
While the subject of personhood has been exhaustively debated regarding the unborn, personhood for sentient animals and artificial intelligences is a concept that is rarely deliberated. Humanity has learned that there are multiple animal species which are very similar to humans in their self-awareness, emotional capacity, and free will. These traits have been partially developed for artificial intelligences as well, and those characteristics will evolve alongside human and technological development. As stratified societies emerged, there have been multiple occurrences where individuals were deemed lesser but then later acquired equal standing. Dr. Daniel Wilson, roboticist, wrote in his novel Robopocalypse, “It …
Semantic Description Of Activities In Videos, Fillipe Dias Moreira De Souza
Semantic Description Of Activities In Videos, Fillipe Dias Moreira De Souza
USF Tampa Graduate Theses and Dissertations
Description of human activities in videos results not only in detection of actions and objects but also in identification of their active semantic relationships in the scene. Towards this broader goal, we present a combinatorial approach that assumes availability of algorithms for detecting and labeling objects and actions, albeit with some errors. Given these uncertain labels and detected objects, we link them into interpretative structures using domain knowledge encoded with concepts of Grenander’s general pattern theory. Here a semantic video description is built using basic units, termed generators, that represent labels of objects or actions. These generators have multiple out-bonds, …
An Approach To Robust Homing With Stereovision, Fuqiang Fu, Damian Lyons
An Approach To Robust Homing With Stereovision, Fuqiang Fu, Damian Lyons
Faculty Publications
Visual Homing is a bioinspired approach to robot navigation which can be fast and uses few assumptions. However, visual homing in a cluttered and unstructured outdoor environment offers several challenges to homing methods that have been developed for primarily indoor environments. One issue is that any current image during homing may be tilted with respect to the home image. The second is that moving through a cluttered scene during homing may cause obstacles to interfere between the home scene and location and the current scene and location. In this paper, we introduce a robust method to improve a previous developed …
Disruption: The New Norm?, Singapore Management University
Disruption: The New Norm?, Singapore Management University
Perspectives@SMU
Accelerating automisation and increasing lifespans are creating disruptions to existing economic and education models. How can governments and industry address the resulting upheavals?
Knowing How: A Computational Approach, Joseph A. Roman
Knowing How: A Computational Approach, Joseph A. Roman
Student Publications
With advances in Artificial Intelligences being achieved through the use of Artificial Neural Networks, we are now at the point where computers are able to do tasks that were previously only able to be accomplished by humans. These advancements must cause us to reconsider our previous understanding of how people come to know how to do a particular task. In order to unpack this question, I will first look to an account of knowing how presented by Jason Stanley in his book Know How. I will then look towards criticisms of this view before using evidence presented by the existence …
A Compare-Aggregate Model For Matching Text Sequences, Shuohang Wang, Jing Jiang
A Compare-Aggregate Model For Matching Text Sequences, Shuohang Wang, Jing Jiang
Research Collection School Of Computing and Information Systems
Many NLP tasks including machine comprehension, answer selection and text entailment require the comparison between sequences. Matching the important units between sequences is a key to solve these problems. In this paper, we present a general "compare-aggregate" framework that performs word-level matching followed by aggregation using Convolutional Neural Networks. We particularly focus on the different comparison functions we can use to match two vectors. We use four different datasets to evaluate the model. We find that some simple comparison functions based on element-wise operations can work better than standard neural network and neural tensor network.
Machine Comprehension Using Match-Lstm And Answer Pointer, Shuohang Wang, Jing Jiang
Machine Comprehension Using Match-Lstm And Answer Pointer, Shuohang Wang, Jing Jiang
Research Collection School Of Computing and Information Systems
Machine comprehension of text is an important problem in natural language processing. A recently released dataset, the Stanford Question Answering Dataset (SQuAD), offers a large number of real questions and their answers created by humans through crowdsourcing. SQuAD provides a challenging testbed for evaluating machine comprehension algorithms, partly because compared with previous datasets, in SQuAD the answers do not come from a small set of candidate answers and they have variable lengths. We propose an end-to-end neural architecture for the task. The architecture is based on match-LSTM, a model we proposed previously for textual entailment, and Pointer Net, a sequence-to-sequence …
Discovering Anomalous Events From Urban Informatics Data, Kasthuri Jayarajah, Vigneshwaran Subbaraju, Dulanga Kaveesha Weerakoon Mudiyanselage, Archan Misra, La Thanh Tam, Noel Athaide
Discovering Anomalous Events From Urban Informatics Data, Kasthuri Jayarajah, Vigneshwaran Subbaraju, Dulanga Kaveesha Weerakoon Mudiyanselage, Archan Misra, La Thanh Tam, Noel Athaide
Research Collection School Of Computing and Information Systems
Singapore's "smart city" agenda is driving the government to provide public access to a broader variety of urban informatics sources, such as images from traffic cameras and information about buses servicing different bus stops. Such informatics data serves as probes of evolving conditions at different spatiotemporal scales. This paper explores how such multi-modal informatics data can be used to establish the normal operating conditions at different city locations, and then apply appropriate outlier-based analysis techniques to identify anomalous events at these selected locations. We will introduce the overall architecture of sociophysical analytics, where such infrastructural data sources can be combined …
Aerial Water Sampler, Carrick Detweiler, John-Paul Ore, Baoliang Zhao, Sebastian Elbaum
Aerial Water Sampler, Carrick Detweiler, John-Paul Ore, Baoliang Zhao, Sebastian Elbaum
School of Computing: Faculty Publications
In one aspect, a vehicle includes an aerial propulsion system, an altitude sensor system, a water sampling system, and a control system. The water sampling system includes a water sampling extension configured to extend away from the vehicle, one or more water sample receptacles, and a water pump. The control system is configured to perform operations including: guiding, using the aerial propulsion system, the vehicle over a water Source; causing, using sensor data from the altitude sensor system, the vehicle to descend towards the water source so that the water sampling extension contacts the water source; and causing, using the …
A Sandbox In Which To Learn And Develop Soar Agents, Daniel Lugo
A Sandbox In Which To Learn And Develop Soar Agents, Daniel Lugo
Theses and Dissertations
It is common for military personnel to leverage simulations (and simulators) as cost-effective tools to train and become proficient at various tasks (e.g., flying an aircraft and/or performing a mission, among others). These training simulations often need to represent humans within the simulated world in a realistic manner. Realistic implies creating simulated humans that exhibit behaviors that mimic real-world decision making and actions. Typically, to create the decision-making logic, techniques developed from the domain of artificial intelligence are used. Although there are several approaches to developing intelligent agents; we focus on leveraging and open source project called Soar, to define …
Vision-Based Mobile Robotic Platform For Autonomous Landing Of Quadcopters, Timothy R. Joe
Vision-Based Mobile Robotic Platform For Autonomous Landing Of Quadcopters, Timothy R. Joe
UNO Student Research and Creative Activity Fair
This project deals with the development of a vision-based control algorithm to assist quadcopters in the landing process. For demonstration purposes, the approach has been implemented in a mobile robotic platform (turtlebot). In this project, the objective is to use the mobile robot as a landing platform. The camera on-board the mobile robot detects the quadcopter (AprilTag attached to the flying robot) and keeps track of it. Based on this idea, the proposed approach estimates in real-time the landing zone. Once this zone is calculated, the mobile robot moves towards this area, stops under the quadcopter, and acts as a …
Passive Chemical Detection System For Uavs, John Hare 2185222
Passive Chemical Detection System For Uavs, John Hare 2185222
UNO Student Research and Creative Activity Fair
In this project we address the problem of autonomously detecting airborne gas particles using gas sensors that are mobilized using unmanned aerial vehicles (UAVs). The main hypothesis we investigate is whether a commercially available, off-the-shelf gas sensor can be suitably integrated on a UAV platform to detect ambient gas particles. The main challenges in this problem include addressing the weight constraints of the UAV’s payload and registering a consistent reading on the gas sensor in the presence of the turbulence in the air caused by the UAV’s rotors. To verify our hypothesis, we designed a passive funneling mechanism for airborne …
A Modular Robotic System For Assessment And Exercise Of Human Movement, Mohan Sai Ambati
A Modular Robotic System For Assessment And Exercise Of Human Movement, Mohan Sai Ambati
UNO Student Research and Creative Activity Fair
This project targets the problem of developing a wearable modular robotic system, for assessing human movement and providing different types of exercises for the user. The system attempts to provide not only a variety of exercises (concentric, eccentric, assisted and resisted), but also to assess the change in variability of the movement as the subject shows functional improvement. The system will not only be useful for patients with sensorimotor problem such as stroke, Parkinson’s, cerebral palsy, but also for special populations such as astronauts who spend long periods of time in space and experience muscle atrophy. In this work, a …
Privacy In Context-Aware Mobile Crowdsourcing Systems, Thivya Kandappu, Archan Misra, Shih-Fen Cheng, Hoong Chuin Lau
Privacy In Context-Aware Mobile Crowdsourcing Systems, Thivya Kandappu, Archan Misra, Shih-Fen Cheng, Hoong Chuin Lau
Research Collection School Of Computing and Information Systems
Mobile crowd-sourcing can become as a strategy to perform time-sensitive urban tasks (such as municipal monitoring and last mile logistics) by effectively coordinating smartphone users. The success of the mobile crowd-sourcing platform depends mainly on its effectiveness in engaging crowd-workers, and recent studies have shown that compared to the pull-based approach, which relies on crowd-workers to browse and commit to tasks they would want to perform, the push-based approach can take into consideration of worker’s daily routine, and generate highly effective recommendations. As a result, workers waste less time on detours, plan more in advance, and require much less planning …
The Wonders Of The Spreadsheet Tool For Data Management And Insights, Michelle L. F. Cheong
The Wonders Of The Spreadsheet Tool For Data Management And Insights, Michelle L. F. Cheong
Research Collection School Of Computing and Information Systems
Ask any student at the Singapore Management University (SMU) toname one of the most practical and useful courses offered by theuniversity. The answer would inevitably include CAT. CAT stands forthe "Computer as an Analysis Tool" course. Originally based on acourse of the same title offered by the Wharton Business School, thefocus of CAT was shifted to provide business students the essentialpractical skills and necessary “real-world” exposure to better usepersonal computers for resolving business problems. The course isbasically centred on using the Excel spreadsheet to work onambiguous ill-defined problems (Leong & Cheong, 2009). Over theyears, three editions of a textbook have …
Feature Learning Via Partial Differential Equation With Applications To Face Recognition, Cong Fang, Zhenyu Zhao, Pan Zhou, Zhouchen Lin
Feature Learning Via Partial Differential Equation With Applications To Face Recognition, Cong Fang, Zhenyu Zhao, Pan Zhou, Zhouchen Lin
Research Collection School Of Computing and Information Systems
Feature learning is a critical step in pattern recognition, such as image classification. However, most of the existing methods cannot extract features that are discriminative and at the same time invariant under some transforms. This limits the classification performance, especially in the case of small training sets. To address this issue, in this paper we propose a novel Partial Differential Equation (PDE) based method for feature learning. The feature learned by our PDE is discriminative, also translationally and rotationally invariant, and robust to illumination variation. To our best knowledge, this is the first work that applies PDE to feature learning …
Directed Acyclic Graph Continuous Max-Flow Image Segmentation For Unconstrained Label Orderings, John Sh Baxter, Martin Rajchl, A. Jonathan Mcleod, Jing Yuan, Terry M. Peters
Directed Acyclic Graph Continuous Max-Flow Image Segmentation For Unconstrained Label Orderings, John Sh Baxter, Martin Rajchl, A. Jonathan Mcleod, Jing Yuan, Terry M. Peters
Robarts Imaging Publications
Label ordering, the specification of subset–superset relationships for segmentation labels, has been of increasing interest in image segmentation as they allow for complex regions to be represented as a collection of simple parts. Recent advances in continuous max-flow segmentation have widely expanded the possible label orderings from binary background/foreground problems to extendable frameworks in which the label ordering can be specified. This article presents Directed Acyclic Graph Max-Flow image segmentation which is flexible enough to incorporate any label ordering without constraints. This framework uses augmented Lagrangian multipliers and primal–dual optimization to develop a highly parallelized solver implemented using GPGPU. This …
Exploring Algorithms To Recognize Similar Board States In Arimaa, Malik Khaleeque Ahmed
Exploring Algorithms To Recognize Similar Board States In Arimaa, Malik Khaleeque Ahmed
Theses and Dissertations
The game of Arimaa was invented as a challenge to the field of game-playing artificial intelligence, which had grown somewhat haughty after IBM's supercomputer Deep Blue trounced world champion Kasparov at chess. Although Arimaa is simple enough for a child to learn and can be played with an ordinary chess set, existing game-playing algorithms and techniques have had a difficult time rising up to the challenge of defeating the world's best human Arimaa players, mainly due to the game's impressive branching factor. This thesis introduces and analyzes new algorithms and techniques that attempt to recognize similar board states based on …
Collective Multiagent Sequential Decision Making Under Uncertainty, Duc Thien Nguyen, Akshat Kumar, Hoong Chuin Lau
Collective Multiagent Sequential Decision Making Under Uncertainty, Duc Thien Nguyen, Akshat Kumar, Hoong Chuin Lau
Research Collection School Of Computing and Information Systems
Multiagent sequential decision making has seen rapid progress with formal models such as decentralized MDPs and POMDPs. However, scalability to large multiagent systems and applicability to real world problems remain limited. To address these challenges, we study multiagent planning problems where the collective behavior of a population of agents affects the joint-reward and environment dynamics. Our work exploits recent advances in graphical models for modeling and inference with a population of individuals such as collective graphical models and the notion of finite partial exchangeability in lifted inference. We develop a collective decentralized MDP model where policies can be computed based …
Recurrent Neural Networks With Auxiliary Labels For Cross-Domain Opinion Target Extraction, Ying Ding, Jianfei Yu, Jing Jiang
Recurrent Neural Networks With Auxiliary Labels For Cross-Domain Opinion Target Extraction, Ying Ding, Jianfei Yu, Jing Jiang
Research Collection School Of Computing and Information Systems
Opinion target extraction is a fundamental task in opinion mining. In recent years, neural network based supervised learning methods have achieved competitive performance on this task. However, as with any supervised learning method, neural network based methods for this task cannot work well when the training data comes from a different domain than the test data. On the other hand, some rule-based unsupervised methods have shown to be robust when applied to different domains. In this work, we use rule-based unsupervised methods to create auxiliary labels and use neural network models to learn a hidden representation that works well for …