Physical Sciences and Mathematics Commons^™

Convergence Of A Reinforcement Learning Algorithm In Continuous Domains, Stephen Carden

All Dissertations

In the field of Reinforcement Learning, Markov Decision Processes with a finite number of states and actions have been well studied, and there exist algorithms capable of producing a sequence of policies which converge to an optimal policy with probability one. Convergence guarantees for problems with continuous states also exist. Until recently, no online algorithm for continuous states and continuous actions has been proven to produce optimal policies. This Dissertation contains the results of research into reinforcement learning algorithms for problems in which both the state and action spaces are continuous. The problems to be solved are introduced formally as …

Collaborative Online Multitask Learning, Guangxia Li, Steven C. H. Hoi, Kuiyu Chang, Wenting Liu, Ramesh Jain

Research Collection School Of Computing and Information Systems

We study the problem of online multitask learning for solving multiple related classification tasks in parallel, aiming at classifying every sequence of data received by each task accurately and efficiently. One practical example of online multitask learning is the micro-blog sentiment detection on a group of users, which classifies micro-blog posts generated by each user into emotional or non-emotional categories. This particular online learning task is challenging for a number of reasons. First of all, to meet the critical requirements of online applications, a highly efficient and scalable classification solution that can make immediate predictions with low learning cost is …

A Continuous Learning Strategy For Self-Organizing Maps Based On Convergence Windows, Gregory T. Breard

Senior Honors Projects

A self-organizing map (SOM) is a type of artificial neural network that has applications in a variety of fields and disciplines. The SOM algorithm uses unsupervised learning to produce a low-dimensional representation of high- dimensional data. This is done by 'fitting' a grid of nodes to a data set over a fixed number of iterations. With each iteration, the nodes of the map are adjusted so that they appear more like the data points. The low-dimensionality of the resulting map means that it can be presented graphically and be more intuitively interpreted by humans. However, it is still essential to …

Evolutionary Algorithm Based Approach For Modeling Autonomously Trading Agents, Anil Yaman, Stephen Lucci, Izidor Gertner

Publications and Research

The autonomously trading agents described in this paper produce a decision to act such as: buy, sell or hold, based on the input data. In this work, we have simulated autonomously trading agents using the Echo State Network (ESNs) model. We generate a collection of trading agents that use different trading strategies using Evolutionary Programming (EP). The agents are tested on EUR/ USD real market data. The main goal of this study is to test the overall performance of this collection of agents when they are active simultaneously. Simulation results show that using different agents concurrently outperform a single agent …

Adapting In-Game Agent Behavior By Observation Of Players Using Learning Behavior Trees, Emmett Tomai, Roberto Flores

Computer Science Faculty Publications

In this paper we describe Learning Behavior Trees, an extension of the popular game AI scripting technique. Behavior Trees provide an effective way for expert designers to describe complex, in-game agent behaviors. Scripted AI captures human intuition about the structure of behavioral decisions, but suffers from brittleness and lack of the natural variation seen in human players. Learning Behavior Trees are designed by a human designer, but then are trained by observation of players performing the same role, to introduce human-like variation to the decision structure. We show that, using this model, a single hand-designed Behavior Tree can cover a …

Intelligent Sensing Based On Low Cost Unmanned Aerial Vehicles (Uav) For Bridge Condition Assessment, Theodore Teates, Austin Boyd, Chung-Hao Chen

Electrical & Computer Engineering Faculty Publications

The eventual completion of this project envisions the use of an Unmanned Aerial Vehicle (UAV) to inspect bridge infrastructure. This project may also be expanded to encompass general object detection and inspection in order to unburden this technology so that it may reach its fullest potential. The project requires research and development in three distinct areas of image processing, control structures, and integration of systems. Initial undergraduate research sets the base knowledge for the overall project, explores the areas of concentration that are desired to expand upon in the future project, and provides a base UAV model that new researchers …

Fuzzy Search Strategy Generation For Adversarial Systems Using Fuzzy Process Particle Swarm Optimization, Fuzzy Patterns, And A Hunch Factor, Stephany Coffman-Wolph

Dissertations

Adversarial game-playing situations have been studied in both game theory and artificial intelligence since the 1950s. However, developing strategies for game playing is challenging due to the large search tree size as the environment size increases. The research presented develops a centralized fuzzy search strategy to find winning strategies for adversarial situations using fuzzy logic. The aforementioned fuzzy algorithm, Fuzzy Strategy Finder (FSF), can be used to find valid strategies for any problem that can be written as a Reti-like or zero-sum game. Using several chess endgames, the FSF will be shown to have a faster runtime without a significant …

Reasoning Across Language And Vision In Machines And Humans, Andrei Barbu

Open Access Dissertations

Humans not only outperform AI and computer-vision systems, but use an unknown computational mechanism to perform tasks for which no suitable approaches exist. I present work investigating both novel tasks and how humans approach them in the context of computer vision and linguistics. I demonstrate a system which, like children, acquires high-level linguistic knowledge about the world. Robots learn to play physically-instantiated board games and use that knowledge to engage in physical play. To further integrate language and vision I develop an approach which produces rich sentential descriptions of events depicted in videos. I then show how to simultaneously detect …

Computer Sketch Recognition, Richard Steigerwald

Master's Theses

Tens of thousands of years ago, humans drew sketches that we can see and identify even today. Sketches are the oldest recorded form of human communication and are still widely used. The universality of sketches supersedes that of culture and language. Despite the universal accessibility of sketches by humans, computers are unable to interpret or even correctly identify the contents of sketches drawn by humans with a practical level of accuracy.

In my thesis, I demonstrate that the accuracy of existing sketch recognition techniques can be improved by optimizing the classification criteria. Current techniques classify a 20,000 sketch crowd-sourced dataset …

Training An Asymmetric Signal Perceptron In An Artificial Chemistry, Peter Banda

Student Research Symposium

Autonomous learning implemented purely by means of a synthetic chemical system has not been previously realized. Learning promotes reusability, and minimizes the system design to simple input-output specification. In this poster, I present a simulated chemical system, the first full-featured implementation of a perceptron in an artificial (simulated) chemistry, which can successfully learn all 14 linearly separable logic functions. A perceptron is the simplest system capable of learning inspired by the functioning of a biological neuron. My newest model called the asymmetric signal perceptron (ASP) is, as opposed to its predecessors such as the weight-race perceptron (WRP), substantially simpler by …

Artificial Immune Systems And Particle Swarm Optimization For Solutions To The General Adversarial Agents Problem, Jeremy Mange

Dissertations

The general adversarial agents problem is an abstract problem description touching on the fields of Artificial Intelligence, machine learning, decision theory, and game theory. The goal of the problem is, given one or more mobile agents, each identified as either “friendly" or “enemy", along with a specified environment state, to choose an action or series of actions from all possible valid choices for the next “timestep" or series thereof, in order to lead toward a specified outcome or set of outcomes. This dissertation explores approaches to this problem utilizing Artificial Immune Systems, Particle Swarm Optimization, and hybrid approaches, along with …

Interpreting Individual Classifications Of Hierarchical Networks, Will Landecker, Michael David Thomure, Luis M.A. Bettencourt, Melanie Mitchell, Garrett T. Kenyon, Steven P. Brumby

Computer Science Faculty Publications and Presentations

Hierarchical networks are known to achieve high classification accuracy on difficult machine-learning tasks. For many applications, a clear explanation of why the data was classified a certain way is just as important as the classification itself. However, the complexity of hierarchical networks makes them ill-suited for existing explanation methods. We propose a new method, contribution propagation, that gives per-instance explanations of a trained network's classifications. We give theoretical foundations for the proposed method, and evaluate its correctness empirically. Finally, we use the resulting explanations to reveal unexpected behavior of networks that achieve high accuracy on visual object-recognition tasks using well-known …

Cancer Risk Analysis By Fuzzy Logic Approach And Performance Status Of The Model, Atinç Yilmaz, Kürşat Ayan

Turkish Journal of Electrical Engineering and Computer Sciences

Cancer is the leading life-threatening disease for people in today's world. Although cancer formation is different for each type of cancer, it has been determined by studies and research that stress also triggers cancer types. Early precaution is very important for people who have not fallen ill yet with a disease like cancer that has a high mortality rate and expensive treatment. With this study, we expound that the possibility of developing such disease may be decreased and people could take measures against it. For the 3 cancer types selected as pilot work by introducing a fuzzy logic model, the …

A New Intelligent Classifier For Breast Cancer Diagnosis Based On A Rough Set And Extreme Learning Machine: Rs + Elm, Yilmaz Kaya

Turkish Journal of Electrical Engineering and Computer Sciences

Breast cancer is one of the leading causes of death among women all around the world. Therefore, true and early diagnosis of breast cancer is an important problem. The rough set (RS) and extreme learning machine (ELM) methods were used collectively in this study for the diagnosis of breast cancer. The unnecessary attributes were discarded from the dataset by means of the RS approach. The classification process by means of ELM was performed using the remaining attributes. The Wisconsin Breast Cancer dataset (WBCD), derived from the University of California Irvine machine learning database, was used for the purpose of testing …

Mobile Games With Intelligence: A Killer Application?, Philip Hingston, Clare Bates Congdon, Graham Kendall

Research outputs 2013

Mobile gaming is an arena full of innovation, with developers exploring new kinds of games, with new kinds of interaction between the mobile device, players, and the connected world that they live in and move through. The mobile gaming world is a perfect playground for AI and CI, generating a maelstrom of data for games that use adaptation, learning and smart content creation. In this paper, we explore this potential killer application for mobile intelligence. We propose combining small, light-weight AI/CI libraries with AI/CI services in the cloud for the heavy lifting. To make our ideas more concrete, we describe …

Testing A Distributed Denial Of Service Defence Mechanism Using Red Teaming, Samaneh Rastegari, Philip Hingston, Chiou-Peng Lam, Murray Brand

Research outputs 2013

The increased number of security threats against the Internet has made communications more vulnerable to attacks. Despite much research and improvement in network security, the number of denial of service (DoS) attacks has rapidly grown in frequency, severity, and sophistication in recent years. Thus, serious attention needs to be paid to network security. However, to create a secure network that can stay ahead of all threats, detection and response features are real challenges. In this paper, we look at the the interaction between the attacker and the defender in a Red Team/Blue Team exercise. We also propose a quantitative decision …

Artificial Intelligence And Data Mining: Algorithms And Applications, Jianhong Xia, Fuding Xie, Yong Zhang, Craig Caulfield

Research outputs 2013

Artificial intelligence and data mining techniques have been used in many domains to solve classification, segmentation, association, diagnosis, and prediction problems. The overall aim of this special issue is to open a discussion among researchers actively working on algorithms and applications. The issue covers a wide variety of problems for computational intelligence, machine learning, time series analysis, remote sensing image mining, and pattern recognition. After a rigorous peer review process, 20 papers have been selected from 38 submissions. The accepted papers in this issue addressed the following topics: (i) advanced artificial intelligence and data mining techniques; (ii) computational intelligence in …

Generalizing Agent Plans And Behaviors With Automated Staged Observation In The Real-Time Strategy Game Starcraft, Zackary A. Gill

Theses and Dissertations - UTB/UTPA

In this thesis we investigate the processes involved in learning to play a game. It was inspired by two observations about how human players learn to play. First, learning the domain is intertwined with goal pursuit. Second, games are designed to ramp up in complexity, walking players through a gradual cycle of acquiring, refining, and generalizing knowledge about the domain. This approach does not rely on traces of expert play. We created an integrated planning, learning and execution system that uses StarCraft as its domain. The planning module creates command/event groupings based on the data received. Observations of unit behavior …

Multiview Semi-Supervised Learning With Consensus, Guangxia Li, Kuiyu Chang, Steven C. H. Hoi

Research Collection School Of Computing and Information Systems

Obtaining high-quality and up-to-date labeled data can be difficult in many real-world machine learning applications. Semi-supervised learning aims to improve the performance of a classifier trained with limited number of labeled data by utilizing the unlabeled ones. This paper demonstrates a way to improve the transductive SVM, which is an existing semi-supervised learning algorithm, by employing a multiview learning paradigm. Multiview learning is based on the fact that for some problems, there may exist multiple perspectives, so called views, of each data sample. For example, in text classification, the typical view contains a large number of raw content features such …

Correct Reasoning: Essays On Logic-Based Ai In Honour Of Vladimir Lifschitz, Esta Erdem, Joohyung Lee, Yuliya Lierler, David Pearce

Faculty Books and Monographs

Co-edited by Yuliya Lierler, UNO faculty member.

Essay, Parsing Combinatory Categorial Grammar via Planning in Answer Set Programming, co-authored by Yuliya Lierler, UNO faculty member.

This Festschrift published in honor of Vladimir Lifschitz on the occasion of his 65th birthday presents 39 articles by colleagues from all over the world with whom Vladimir Lifschitz had cooperation in various respects. The 39 contributions reflect the breadth and the depth of the work of Vladimir Lifschitz in logic programming, circumscription, default logic, action theory, causal reasoning and answer set programming.

Comparing Ai Archetypes And Hybrids Using Blackjack, Robert Edward Noonan

All Graduate Theses, Dissertations, and Other Capstone Projects

The discipline of artificial intelligence (AI) is a diverse field, with a vast variety of philosophies and implementations to consider. This work attempts to compare several of these paradigms as well as their variations and hybrids, using the card game of blackjack as the field of competition. This is done with an automated blackjack emulator, written in Java, which accepts computer-controlled players of various AI philosophies and their variants, training them and finally pitting them against each other in a series of tournaments with customizable rule sets. In order to avoid bias towards any particular implementation, the system treats each …

Parsing Combinatory Categorial Grammar Via Planning In Answer Set Programming, Yuliya Lierler, Peter Schueller

Computer Science Faculty Books and Monographs

Essay, Parsing Combinatory Categorial Grammar via Planning in Answer Set Programming, from Correct reasoning: essays on logic-based AI in honour of Vladimir Lifschitz, co-authored by Yuliya Lierler, UNO faculty member. Combinatory categorial grammar (CCG) is a grammar formalism used for natural language parsing. CCG assigns structured lexical categories to words and uses a small set of combinatory rules to combine these categories to parse a sentence. In this work we propose and implement a new approach to CCG parsing that relies on a prominent knowledge representation formalism, answer set programming (ASP) - a declarative programming paradigm. We formulate the …

Using Monte Carlo Tree Search For Replanning In A Multistage Simultaneous Game, Daniel Beard, Philip Hingston, Martin Masek

Research outputs 2012

In this study, we introduce MC-TSAR, a Monte Carlo Tree Search algorithm for strategy selection in simultaneous multistage games. We evaluate the algorithm using a battle planning scenario in which replanning is possible. We show that the algorithm can be used to select a strategy that approximates a Nash equilibrium strategy, taking into account the possibility of switching strategies part way through the execution of the scenario in the light of new information on the progress of the battle.

A Multimodal Problem For Competitive Coevolution, Philip Hingston, Tirtha Ranjeet, Chiou Peng Lam, Martin Masek

Research outputs 2012

Coevolutionary algorithms are a special kind of evolutionary algorithm with advantages in solving certain specific kinds of problems. In particular, competitive coevolutionary algorithms can be used to study problems in which two sides compete against each other and must choose a suitable strategy. Often these problems are multimodal - there is more than one strong strategy for each side. In this paper, we introduce a scalable multimodal test problem for competitive coevolution, and use it to investigate the effectiveness of some common coevolutionary algorithm enhancement techniques.

Object Retrieval From Secure Unknown Interior Spaces Using Autonomous Unmanned Aerial Vehicles, John Levous, Julie Hoven, Victor Habgood, Abdulrahman Alotaibi, Brandon Ordway, Garibe Mohammed-Jones, Haole Guo, Filip Cuckov, Chung-Hao Chen

Electrical & Computer Engineering Faculty Publications

This paper describes an autonomous unmanned aerial vehicle (UAV) designed to participate in the 23rd annual International Aerial Robotics Competition. The UAV is equipped with onboard sensors and a Harvard architecture 8-bit RISC microcontroller to monitor and locally control its flight telemetry. Additional sensors (and an additional microcontroller) are used for detecting and mapping of structural and environmental objects while the UAV is in flight. The microcontrollers are interfaced with wireless communication modules for transmitting flight telemetry and structural/environmental data to a ground control station that sends the UAV command and control signals required for the mission objectives. The UAV …

Report On Advances In The Field Of Artificial Intelligence Attributed To Captcha, Craig M. Schow

All Graduate Plan B and other Reports, Spring 1920 to Spring 2023

A CAPTCHA is a specialized human interaction proof that exploits gaps between human and computer recognition abilities. By design, the hardness of a CAPTCHA is based on the difficulty of advancing the underlying artificial intelligence [AI] technology to a level that eliminates any exploitable gap. Due to this fact computer scientists have concluded that the widespread use of CAPTCHA would accelerate research in the underlying fields of AI eventually leading to near-­‐human capabilities in certain AI systems. Despite these predictions no attempt has been made to identify advances in AI which can be attributed to the use of CAPTCHA.

The …

Chatbots In The Library: Is It Time?, Deeann Allison

University of Nebraska-Lincoln Libraries: Faculty Publications

This paper describes a pilot at the University of Nebraska-Lincoln for a chatbot that answers questions about the library and library resources. The chatbot was developed using a SQL database to store the question and answers using Artificial Intelligence Mark-up Language metadata. The user interface was built using PHP, adapted from Program-O. The open source PHP program was modified to support better display and the launching of URLs within the chatbot screen. Database content was created by “mining” library websites for information, and analyzing chat logs.

The chatbot answers questions from a variety of users from around the world. It …

Single And Multiobjective Approaches To Clustering With Point Symmetry., Sriparna Saha Dr.

Doctoral Theses

In our every day life, we make decisions consciously or unconsciously. This decision can be very simple such as selecting the color of dress or deciding the menu for lunch, or may be as difficult as those involved in designing a missile or in selecting a career. The former decision is easy to take, while the latter one might take several years due to the level of complexity involved in it. The main goal of most kinds of decision-making is to optimize one or more criteria in order to achieve the desired result. In other words, problems related to optimization …

Partitioning Of Minimotifs Based On Function With Improved Prediction Accuracy, Sanguthevar Rajasekaran, Tian Mi, Jerlin Camilus Merlin, Aaron Oommen, Patrick R. Gradie, Martin R. Schiller

Life Sciences Faculty Research

Background

Minimotifs are short contiguous peptide sequences in proteins that are known to have a function in at least one other protein. One of the principal limitations in minimotif prediction is that false positives limit the usefulness of this approach. As a step toward resolving this problem we have built, implemented, and tested a new data-driven algorithm that reduces false-positive predictions.

Methodology/Principal Findings

Certain domains and minimotifs are known to be strongly associated with a known cellular process or molecular function. Therefore, we hypothesized that by restricting minimotif predictions to those where the minimotif containing protein and target protein have …

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 …