Open Access. Powered by Scholars. Published by Universities.®
Physical Sciences and Mathematics Commons™
Open Access. Powered by Scholars. Published by Universities.®
- Institution
-
- Singapore Management University (2961)
- Wright State University (632)
- Walden University (447)
- Selected Works (287)
- New Jersey Institute of Technology (137)
-
- University of Nebraska at Omaha (119)
- California State University, San Bernardino (96)
- Old Dominion University (95)
- San Jose State University (85)
- University of Dayton (82)
- The University of Maine (67)
- City University of New York (CUNY) (65)
- University of Nebraska - Lincoln (54)
- Air Force Institute of Technology (53)
- SelectedWorks (53)
- Technological University Dublin (51)
- University of South Florida (50)
- Kennesaw State University (46)
- Nova Southeastern University (43)
- Claremont Colleges (42)
- University of Wisconsin Milwaukee (42)
- University of Arkansas, Fayetteville (41)
- Western Kentucky University (41)
- Dakota State University (39)
- Institute of Business Administration (38)
- California Polytechnic State University, San Luis Obispo (36)
- Western University (35)
- Ateneo de Manila University (34)
- Governors State University (34)
- Purdue University (34)
- Keyword
-
- Machine learning (101)
- Information technology (93)
- Data mining (89)
- Social media (78)
- Twitter (64)
-
- Machine Learning (57)
- Cybersecurity (54)
- Semantic Web (54)
- Deep learning (52)
- Artificial intelligence (49)
- Online learning (49)
- Information Technology (47)
- Classification (46)
- Cloud computing (45)
- Information retrieval (45)
- Privacy (45)
- Big data (44)
- Database (43)
- Ontology (43)
- Computer science (42)
- Information security (41)
- Algorithms (40)
- Security (40)
- Databases (39)
- Information systems (39)
- Management (37)
- Clustering (36)
- Data Mining (36)
- Northern Ohio Data and Information Service (NODIS) (36)
- Technology (35)
- Publication Year
- Publication
-
- Research Collection School Of Computing and Information Systems (2867)
- Kno.e.sis Publications (541)
- Walden Dissertations and Doctoral Studies (447)
- Theses and Dissertations (116)
- Dissertations (107)
-
- Computer Science Faculty Publications (91)
- Computer Science and Engineering Faculty Publications (91)
- Theses Digitization Project (84)
- Master's Projects (68)
- Information Systems and Quantitative Analysis Faculty Proceedings & Presentations (64)
- Electronic Theses and Dissertations (55)
- Dissertations and Theses Collection (Open Access) (50)
- Theses (46)
- USF Tampa Graduate Theses and Dissertations (46)
- CCE Theses and Dissertations (42)
- Information Systems and Quantitative Analysis Faculty Publications (41)
- Kyriakos MOURATIDIS (40)
- CGU Faculty Publications and Research (37)
- International Conference on Information and Communication Technologies (36)
- Open Educational Resources (34)
- Department of Information Systems & Computer Science Faculty Publications (33)
- All Capstone Projects (32)
- Graduate Theses and Dissertations (32)
- Masters Theses & Doctoral Dissertations (32)
- Articles (29)
- Conference papers (28)
- David LO (28)
- Journal of Spatial Information Science (28)
- All Maxine Goodman Levin School of Urban Affairs Publications (27)
- Saverio Perugini (25)
- Publication Type
Articles 5551 - 5580 of 6720
Full-Text Articles in Physical Sciences and Mathematics
Continuous Medoid Queries Over Moving Objects, Stavros Papadopoulos, Dimitris Sacharidis, Kyriakos Mouratidis
Continuous Medoid Queries Over Moving Objects, Stavros Papadopoulos, Dimitris Sacharidis, Kyriakos Mouratidis
Research Collection School Of Computing and Information Systems
In the k-medoid problem, given a dataset P, we are asked to choose kpoints in P as the medoids. The optimal medoid set minimizes the average Euclidean distance between the points in P and their closest medoid. Finding the optimal k medoids is NP hard, and existing algorithms aim at approximate answers, i.e., they compute medoids that achieve a small, yet not minimal, average distance. Similarly in this paper, we also aim at approximate solutions. We consider, however, the continuous version of the problem, where the points in P move and our task is to maintain the medoid set on-the-fly …
On Searching Continuous Nearest Neighbors In Wireless Data Broadcast Systems, Baihua Zheng, Wang-Chien Lee, Dik Lun Lee
On Searching Continuous Nearest Neighbors In Wireless Data Broadcast Systems, Baihua Zheng, Wang-Chien Lee, Dik Lun Lee
Research Collection School Of Computing and Information Systems
A continuous nearest neighbor (CNN) search, which retrieves the nearest neighbors corresponding to every point in a given query line segment, is important for location-based services such as vehicular navigation and tourist guides. It is infeasible to answer a CNN search by issuing a traditional nearest neighbor query at every point of the line segment due to the large number of queries generated and the overhead on bandwidth. Algorithms have been proposed recently to support CNN search in the traditional client-server systems but not in the environment of wireless data broadcast, where uplink communication channels from mobile devices to the …
Is Interpersonal Trust A Necessary Condition For Organisational Learning?, Siu Loon Hoe
Is Interpersonal Trust A Necessary Condition For Organisational Learning?, Siu Loon Hoe
Research Collection School Of Computing and Information Systems
The organisational behaviour and management literature has devoted a lot attention on various factors affecting organisational learning. While there has been much work done to examine trust in promoting organisational learning, there is a lack of consensus on the specific type of trust involved. The purpose of this paper is to highlight the importance of interpersonal trust in promoting organisational learning and propose a research agenda to test the extent of interpersonal trust on organisational learning. This paper contributes to the existing organisational learning literature by specifying a specific form of trust, interpersonal trust, which promotes organisational learning and proposing …
Continuous Monitoring Of Top-K Queries Over Sliding Windows, Kyriakos Mouratidis, Spiridon Bakiras, Dimitris Papadias
Continuous Monitoring Of Top-K Queries Over Sliding Windows, Kyriakos Mouratidis, Spiridon Bakiras, Dimitris Papadias
Research Collection School Of Computing and Information Systems
Given a dataset P and a preference function f, a top-k query retrieves the k tuples in P with the highest scores according to f. Even though the problem is well-studied in conventional databases, the existing methods are inapplicable to highly dynamic environments involving numerous long-running queries. This paper studies continuous monitoring of top-k queries over a fixed-size window W of the most recent data. The window size can be expressed either in terms of the number of active tuples or time units. We propose a general methodology for top-k monitoring that restricts processing to the sub-domains of the workspace …
Efficient Near-Duplicate Keyframe Retrieval With Visual Language Models, Xiao Wu, Wan-Lei Zhao, Chong-Wah Ngo
Efficient Near-Duplicate Keyframe Retrieval With Visual Language Models, Xiao Wu, Wan-Lei Zhao, Chong-Wah Ngo
Research Collection School Of Computing and Information Systems
Near-duplicate keyframe retrieval is a critical task for video similarity measure, video threading and tracking. In this paper, instead of using expensive point-to-point matching on keypoints, we investigate the visual language models built on visual keywords to speed up the near-duplicate keyframe retrieval. The main idea is to estimate a visual language model on visual keywords for each keyframe and compare keyframes by the likelihood of their visual language models. Experiments on a subset of TRECVID-2004 video corpus show that visual language models built on visual keywords demonstrate promising performance for near-duplicate keyframe retrieval, which greatly speed up the retrieval …
Analyzing Feature Trajectories For Event Detection, Qi He, Kuiyu Chang, Ee Peng Lim
Analyzing Feature Trajectories For Event Detection, Qi He, Kuiyu Chang, Ee Peng Lim
Research Collection School Of Computing and Information Systems
We consider the problem of analyzing word trajectories in both time and frequency domains, with the specific goal of identifying important and less-reported, periodic and aperiodic words. A set of words with identical trends can be grouped together to reconstruct an event in a completely un-supervised manner. The document frequency of each word across time is treated like a time series, where each element is the document frequency - inverse document frequency (DFIDF) score at one time point. In this paper, we 1) first applied spectral analysis to categorize features for different event characteristics: important and less-reported, periodic and aperiodic; …
Cross-Lingual Query Suggestion Using Query Logs Of Different Languages, Wei Gao, Cheng Niu, Jian-Yun Nie, Ming Zhou, Jian Hu, Kam-Fai Wong, Hsiao-Wuen Hon
Cross-Lingual Query Suggestion Using Query Logs Of Different Languages, Wei Gao, Cheng Niu, Jian-Yun Nie, Ming Zhou, Jian Hu, Kam-Fai Wong, Hsiao-Wuen Hon
Research Collection School Of Computing and Information Systems
Query suggestion aims to suggest relevant queries for a given query, which help users better specify their information needs. Previously, the suggested terms are mostly in the same language of the input query. In this paper, we extend it to cross-lingual query suggestion (CLQS): for a query in one language, we suggest similar or relevant queries in other languages. This is very important to scenarios of cross-language information retrieval (CLIR) and cross-lingual keyword bidding for search engine advertisement. Instead of relying on existing query translation technologies for CLQS, we present an effective means to map the input query of one …
Creating Database-Backed Library Web Pages Using Open Source Tools (Review), Frank J. Bove
Creating Database-Backed Library Web Pages Using Open Source Tools (Review), Frank J. Bove
Frank J. Bove
No abstract provided.
Relationship Web: Realizing The Memex Vision With The Help Of Semantic Web, Amit P. Sheth
Relationship Web: Realizing The Memex Vision With The Help Of Semantic Web, Amit P. Sheth
Kno.e.sis Publications
Relationship Web takes us from "which document" could have information I need to "what's in the resources" that gives me the insight and knowledge I need for decision making. Dr. Vannevar Bush outlined his vision for Memex in a 1945 Atlantic Monthly article [1]. Describing how the human brain navigates an information space in what he called trailblazing, Dr. Bush said, "It operates by association. With one item in its grasp, it snaps instantly to the next that is suggested by the association of thoughts, in accordance with some intricate web of trails carried by the cells of the brain." …
Semantics To Empower Services Science: Using Semantics At Middleware, Web Services And Business Levels, Amit P. Sheth
Semantics To Empower Services Science: Using Semantics At Middleware, Web Services And Business Levels, Amit P. Sheth
Kno.e.sis Publications
No abstract provided.
Clustering-Based High Trend Identification In Dataset, Dr. Muhammad Zubair Asghar, Dr. Auranzeb Khan, Fazal Masud Kundi, Nafees Ur Rehman
Clustering-Based High Trend Identification In Dataset, Dr. Muhammad Zubair Asghar, Dr. Auranzeb Khan, Fazal Masud Kundi, Nafees Ur Rehman
Dr. Muhammad Zubair Asghar
Clustering data into meaningful groups has a vast scope of research in several fields, like: statistics, information theory, machine learning, databases, and bioinformatics. This paper presents the modified form of K-means clustering algorithm called T-means. This algorithm creates, sorted clusters and labels as "high trend" and "low trend". Then M cases are selected from the high trend cluster (HTC) to construct the final HTC. The algorithm was tested on real univariate data of student's marks. Experimental results show that T-means can be efficiently used to construct the sorted cluster of significant cases in data set. T-means will help to identify …
Session 2 - Societal-Consciousness In The Computing Curricula: A Time For Serious Introspection, Daniel Moix, Srini Ramaswamy
Session 2 - Societal-Consciousness In The Computing Curricula: A Time For Serious Introspection, Daniel Moix, Srini Ramaswamy
International Symposium on Technology and Society
This paper addresses the growing need for inculcating appropriate ethics within the computing curriculum by fostering the development of a societally-conscious ethical framework among our students to address the use of information technology vis-à-vis government, business and society. We propose a new integrated model based approach (IDEA) and suggest its adoption to encourage students on reflecting upon the social and ethical ramifications of technology, beyond the narrow, project focused tunnel vision that currently (subliminally) exists in many computing curricula, and in particular, in today’s profit-focused, consulting and contract-based software industry.
Automatic Composition Of Semantic Web Services Using Process Mediation, Zixin Wu, Karthik Gomadam, Ajith Harshana Ranabahu, Amit P. Sheth, John A. Miller
Automatic Composition Of Semantic Web Services Using Process Mediation, Zixin Wu, Karthik Gomadam, Ajith Harshana Ranabahu, Amit P. Sheth, John A. Miller
Kno.e.sis Publications
Web service composition has quickly become a key area of research in the services oriented architecture community. One of the challenges in composition is the existence of heterogeneities across independently created and autonomously managed Web service requesters and Web service providers. Previous work in this area either involved significant human effort or in cases of the efforts seeking to provide largely automated approaches, overlooked the problem of data heterogeneities, resulting in partial solutions that would not support executable workflow for real-world problems. In this paper, we present a planning-based approach to solve both the process heterogeneity and data heterogeneity problems. …
Paraconsistent Resolution For Four-Valued Description Logics, Yue Ma, Pascal Hitzler, Zuoquan Li
Paraconsistent Resolution For Four-Valued Description Logics, Yue Ma, Pascal Hitzler, Zuoquan Li
Computer Science and Engineering Faculty Publications
In this paper, we propose an approach to translating any ALC ontology (possible inconsistent) into a logically consistent set of disjunctive datalog rules. We achieve this in two steps: First we give a simple way to make any ALC based ontology 4-valued satisfiable, and then we study a sound and complete paraconsistent ordered-resolution decision procedure for our 4-valued ALC. Our approach can be viewed as a paraconsistent version of KAON2 algorithm.
Foundations Of Refinement Operators For Description Logics, Jens Lehmann, Pascal Hitzler
Foundations Of Refinement Operators For Description Logics, Jens Lehmann, Pascal Hitzler
Computer Science and Engineering Faculty Publications
In order to leverage techniques from Inductive Logic Programming for the learning in description logics (DLs), which are the foundation of ontology languages in the Semantic Web, it is important to acquire a thorough understanding of the theoretical potential and limitations of using refinement operators within the description logic paradigm. In this paper, we present a comprehensive study which analyses desirable properties such operators should have. In particular, we show that ideal refinement operators in general do not exist, which is indicative of the hardness inherent in learning in DLs. We also show which combinations of desirable properties are theoretically …
Algorithms For Paraconsistent Reasoning With Owl, Yue Ma, Pascal Hitzler, Zuoquan Lin
Algorithms For Paraconsistent Reasoning With Owl, Yue Ma, Pascal Hitzler, Zuoquan Lin
Computer Science and Engineering Faculty Publications
In an open, constantly changing and collaborative environment like the forthcoming Semantic Web, it is reasonable to expect that knowledge sources will contain noise and inaccuracies. Practical reasoning techniques for ontologies therefore will have to be tolerant to this kind of data, including the ability to handle inconsistencies in a meaningful way. For this purpose, we employ paraconsistent reasoning based on four-valued logic, which is a classical method for dealing with inconsistencies in knowledge bases. Its transfer to OWL DL, however, necessitates the making of fundamental design choices in dealing with class inclusion, which has resulted in differing proposals for …
A Refinement Operator Based Learning Algorithm For The Alc Description Logic, Jens Lehmann, Pascal Hitzler
A Refinement Operator Based Learning Algorithm For The Alc Description Logic, Jens Lehmann, Pascal Hitzler
Computer Science and Engineering Faculty Publications
With the advent of the Semantic Web, description logics have become one of the most prominent paradigms for knowledge representation and reasoning. Progress in research and applications, however, faces a bottleneck due to the lack of available knowledge bases, and it is paramount that suitable automated methods for their acquisition will be developed. In this paper, we provide the first learning algorithm based on refinement operators for the most fundamental description logic ALC. We develop the algorithm from thorough theoretical foundations and report on a prototype implementation.
Acquisition Of Owl Dl Axioms From Lexical Resources, Johanna Volker, Pascal Hitzler, Philipp Cimiano
Acquisition Of Owl Dl Axioms From Lexical Resources, Johanna Volker, Pascal Hitzler, Philipp Cimiano
Computer Science and Engineering Faculty Publications
State-of-the-art research on automated learning of ontologies from text currently focuses on inexpressive ontologies. The acquisition of complex axioms involving logical connectives, role restrictions, and other expressive features of the Web Ontology Language OWL remains largely unexplored. In this paper, we present a method and implementation for enriching inexpressive OWL ontologies with expressive axioms which is based on a deep syntactic analysis of natural language definitions. We argue that it can serve as a core for a semi-automatic ontology engineering process supported by a methodology that integrates methods for both ontology learning and evaluation. The feasibility of our approach is …
Efficient Owl Reasoning With Logic Programs - Evaluations, Sebastian Rudolph, Markus Krotzsch, Pascal Hitzler, Michael Sintek, Denny Vrandecic
Efficient Owl Reasoning With Logic Programs - Evaluations, Sebastian Rudolph, Markus Krotzsch, Pascal Hitzler, Michael Sintek, Denny Vrandecic
Computer Science and Engineering Faculty Publications
We report on efficiency evaluations concerning two different approaches to using logic programming for OWL [1] reasoning and show, how the two approaches can be combined.
Selecting Labels For News Document Clusters, Krishnaprasad Thirunarayan, Trivikram Immaneni, Mastan Vali Shaik
Selecting Labels For News Document Clusters, Krishnaprasad Thirunarayan, Trivikram Immaneni, Mastan Vali Shaik
Kno.e.sis Publications
This work deals with determination of meaningful and terse cluster labels for News document clusters. We analyze a number of alternatives for selecting headlines and/or sentences of document in a document cluster (obtained as a result of an entity-event-duration query), and formalize an approach to extracting a short phrase from well-supported headlines/sentences of the cluster that can serve as the cluster label. Our technique maps a sentence into a set of significant stems to approximate its semantics, for comparison. Eventually a cluster label is extracted from a selected headline/sentence as a contiguous sequence of words, resuscitating word sequencing information lost …
A Well-Founded Semantics For Hybrid Mknf Knowledge Bases, Matthias Knorr, Jose Julio Alferes, Pascal Hitzler
A Well-Founded Semantics For Hybrid Mknf Knowledge Bases, Matthias Knorr, Jose Julio Alferes, Pascal Hitzler
Computer Science and Engineering Faculty Publications
In [10], hybrid MKNF knowledge bases have been proposed for combining open and closed world reasoning within the logics of minimal knowledge and negation as failure ([8]). For this powerful framework, we define a three-valued semantics and provide an alternating fixpoint construction for nondisjunctive hybrid MKNF knowledge bases. We thus provide a well-founded semantics which is a sound approximation of the cautious MKNF model semantics, and which also features improved computational properties. We also show that whenever the DL knowledge base part is empty, then the alternating fixpoint coincides with the classical well-founded model.
Measuring Inconsistency For Description Logics Based On Paraconsistent Semantics, Yue Ma, Guilin Qi, Pascal Hitzler, Zuoquan Lin
Measuring Inconsistency For Description Logics Based On Paraconsistent Semantics, Yue Ma, Guilin Qi, Pascal Hitzler, Zuoquan Lin
Computer Science and Engineering Faculty Publications
In this paper, we propose an approach for measuring inconsistency in inconsistent ontologies. We first define the degree of inconsistency of an inconsistent ontology using a four-valued semantics for the description logic ALC. Then an ordering over inconsistent ontologies is given by considering their inconsistency degrees. Our measure of inconsistency can provide important information for inconsistency handling.
Runtime Support Of Speculative Optimization For Offline Escape Analysis, Kevin Cleereman, Michelle Cheatham, Krishnaprasad Thirunarayan
Runtime Support Of Speculative Optimization For Offline Escape Analysis, Kevin Cleereman, Michelle Cheatham, Krishnaprasad Thirunarayan
Kno.e.sis Publications
Escape analysis can improve the speed and memory efficiency of garbage collected languages by allocating objects to the call stack, but an offline analysis will potentially interfere with dynamic class loading and an online analysis must sacrifice precision for speed. We describe a technique that permits the safe use of aggressive, speculative offline escape analysis in programs potentially loading classes that violate the analysis results.
A Multi-Scale Tikhonov Regularization Scheme For Implicit Surface Modeling, Jianke Zhu, Steven C. H. Hoi, Michael R. Lyu
A Multi-Scale Tikhonov Regularization Scheme For Implicit Surface Modeling, Jianke Zhu, Steven C. H. Hoi, Michael R. Lyu
Research Collection School Of Computing and Information Systems
Kernel machines have recently been considered as a promising solution for implicit surface modelling. A key challenge of machine learning solutions is how to fit implicit shape models from large-scale sets of point cloud samples efficiently. In this paper, we propose a fast solution for approximating implicit surfaces based on a multi-scale Tikhonov regularization scheme. The optimization of our scheme is formulated into a sparse linear equation system, which can be efficiently solved by factorization methods. Different from traditional approaches, our scheme does not employ auxiliary off-surface points, which not only saves the computational cost but also avoids the problem …
Learning Nonparametric Kernel Matrices From Pairwise Constraints, Steven C. H. Hoi, Rong Jin, Michael R. Lyu
Learning Nonparametric Kernel Matrices From Pairwise Constraints, Steven C. H. Hoi, Rong Jin, Michael R. Lyu
Research Collection School Of Computing and Information Systems
Many kernel learning methods have to assume parametric forms for the target kernel functions, which significantly limits the capability of kernels in fitting diverse patterns. Some kernel learning methods assume the target kernel matrix to be a linear combination of parametric kernel matrices. This assumption again importantly limits the flexibility of the target kernel matrices. The key challenge with nonparametric kernel learning arises from the difficulty in linking the nonparametric kernels to the input patterns. In this paper, we resolve this problem by introducing the graph Laplacian of the observed data as a regularizer when optimizing the kernel matrix with …
Similarity Beyond Distance Measurement, Feng Kang, Rong Jin, Steven C. H. Hoi
Similarity Beyond Distance Measurement, Feng Kang, Rong Jin, Steven C. H. Hoi
Research Collection School Of Computing and Information Systems
One of the keys issues to content-based image retrieval is the similarity measurement of images. Images are represented as points in the space of low-level visual features and most similarity measures are based on certain distance measurement between these features. Given a distance metric, two images with shorter distance are deemed to more similar than images that are far away. The well-known problem with these similarity measures is the semantic gap, namely two images separated by large distance could share the same semantic content. In this paper, we propose a novel similarity measure of images that goes beyond the distance …
Mobile G-Portal Supporting Collaborative Sharing And Learning In Geography Fieldwork: An Empirical Study, Yin-Leng Theng, Kuah-Li Tan, Ee Peng Lim, Jun Zhang, Dion Hoe-Lian Goh, Kalyani Chatterjea, Chew-Hung Chang, Aixin Sun, Han Yu, Nam Hai Dang, Yuanyuan Li, Minh Chanh Vo
Mobile G-Portal Supporting Collaborative Sharing And Learning In Geography Fieldwork: An Empirical Study, Yin-Leng Theng, Kuah-Li Tan, Ee Peng Lim, Jun Zhang, Dion Hoe-Lian Goh, Kalyani Chatterjea, Chew-Hung Chang, Aixin Sun, Han Yu, Nam Hai Dang, Yuanyuan Li, Minh Chanh Vo
Research Collection School Of Computing and Information Systems
Integrated with G-Portal, a Web-based geospatial digital library of geography resources, this paper describes the implementation of Mobile G-Portal, a group of mobile devices as learning assistant tools supporting collaborative sharing and learning for geography fieldwork. Based on a modified Technology Acceptance Model and a Task-Technology Fit model, an initial study with Mobile G-Portal was conducted involving 39 students in a local secondary school. The findings suggested positive indication of acceptance of Mobile G-Portal for geography fieldwork. The paper concludes with a discussion on technological challenges, recommendations for refinement of Mobile G-Portal, and design implications in general for digital libraries …
Continuous Nearest Neighbor Queries Over Sliding Windows, Kyriakos Mouratidis, Dimitris Papadias
Continuous Nearest Neighbor Queries Over Sliding Windows, Kyriakos Mouratidis, Dimitris Papadias
Research Collection School Of Computing and Information Systems
Recent research has focused on continuous monitoring of nearest neighbors (NN) in highly dynamic scenarios, where the queries and the data objects move frequently and arbitrarily. All existing methods, however, assume the Euclidean distance metric. In this paper we study k-NN monitoring in road networks, where the distance between a query and a data object is determined by the length of the shortest path connecting them. We propose two methods that can handle arbitrary object and query moving patterns, as well as fluctuations of edge weights. The first one maintains the query results by processing only updates that may invalidate …
Instance Weighting For Domain Adaptation In Nlp, Jing Jiang, Chengxiang Zhai
Instance Weighting For Domain Adaptation In Nlp, Jing Jiang, Chengxiang Zhai
Research Collection School Of Computing and Information Systems
Domain adaptation is an important problem in natural language processing (NLP) due to the lack of labeled data in novel domains. In this paper, we study the domain adaptation problem from the instance weighting per- spective. We formally analyze and charac- terize the domain adaptation problem from a distributional view, and show that there are two distinct needs for adaptation, cor- responding to the different distributions of instances and classification functions in the source and the target domains. We then propose a general instance weighting frame- work for domain adaptation. Our empir- ical results on three NLP tasks show that …
Intelligence Through Interaction: Towards A Unified Theory For Learning, Ah-Hwee Tan, Gail A. Carpenter, Stephen Grossberg
Intelligence Through Interaction: Towards A Unified Theory For Learning, Ah-Hwee Tan, Gail A. Carpenter, Stephen Grossberg
Research Collection School Of Computing and Information Systems
Machine learning, a cornerstone of intelligent systems, has typically been studied in the context of specific tasks, including clustering (unsupervised learning), classification (supervised learning), and control (reinforcement learning). This paper presents a learning architecture within which a universal adaptation mechanism unifies a rich set of traditionally distinct learning paradigms, including learning by matching, learning by association, learning by instruction, and learning by reinforcement. In accordance with the notion of embodied intelligence, such a learning theory provides a computational account of how an autonomous agent may acquire the knowledge of its environment in a real-time, incremental, and continuous manner. Through a …