Machine Learning is the study of methods for programming computers to learn. Computers are applied to a wide range of tasks, and for most of these it is relatively easy for programmers to design and implement the necessary software. However, there are many tasks for which this is difficult or impossible. These can be divided into four general categories. First, there are problems for which there exist no human experts. For example, in modern automated manufacturing facilities, there is a need to predict machine failures before they occur by analyzing sensor readings. Because the machines are new, there are no human experts who can be interviewed by a programmer to provide the knowledge necessary to build a computer system. A machine learning system can study recorded data and subsequent machine failures and learn prediction rules. Second, there are problems where human experts exist, but where they are unable to explain their expertise. This is the case in many perceptual tasks, such as speech recognition, hand-writing recognition, and natural language understanding. Virtually all humans exhibit expert-level abilities on these tasks, but none of them can describe the detailed steps that they follow as they perform them. Fortunately, humans can provide machines with examples of the inputs and correct outputs for these tasks, so machine learning algorithms can learn to map the inputs to the outputs. Third, there are problems where phenomena are changing rapidly. In finance, for example, people would like to predict the future behavior of the stock market, of consumer purchases, or of exchange rates. These behaviors change frequently, so that even if a programmer could construct a good predictive computer program, it would need to be rewritten frequently. A learning program can relieve the programmer of this burden by constantly modifying and tuning a set of learned prediction rules. Fourth, there are applications that need to be customized for each computer user separately. Consider, for example, a program to filter unwanted electronic mail messages. Different users will need different filters. It is unreasonable to expect each user to program his or her own rules, and it is infeasible to provide every user with a software engineer to keep the rules up-to-date. A machine learning system can learn which mail messages the user rejects and maintain the filtering rules automatically. Machine learning addresses many of the same research questions as the fields of statistics, data mining, and psychology, but with differences of emphasis. Statistics focuses on understanding the phenomena that have generated the data, often with the goal of testing different hypotheses about those phenomena. Data mining seeks to find patterns in the data that are understandable by people. Psychological studies of human learning aspire to understand the mechanisms underlying the various learning behaviors exhibited by people (concept learning, skill acquisition, strategy change, etc.).

Machine learning

25. Multiple Imputation for Nonresponse in Surveys. By D. B. Rubin. ISBN 0 471 08705 X. Wiley, Chichester, 1987. 258 pp. £30.25.

Multiple Imputation for Nonresponse in Surveys

Statistical Analysis with Missing Data

Ontologies tend to be found everywhere. They are viewed as the silver bullet for many applications, such as database integration, peer-to-peer systems, e-commerce, semantic web services, or social networks. However, in open or evolving systems, such as the semantic web, different parties would, in general, adopt different ontologies. Thus, merely using ontologies, like using XML, does not reduce heterogeneity: it just raises heterogeneity problems to a higher level. Euzenat and Shvaikos book is devoted to ontology matching as a solution to the semantic heterogeneity problem faced by computer systems. Ontology matching aims at finding correspondences between semantically related entities of different ontologies. These correspondences may stand for equivalence as well as other relations, such as consequence, subsumption, or disjointness, between ontology entities. Many different matching solutions have been proposed so far from various viewpoints, e.g., databases, information systems, and artificial intelligence. The second edition of Ontology Matching has been thoroughly revised and updated to reflect the most recent advances in this quickly developing area, which resulted in more than 150 pages of new content. In particular, the book includes a new chapter dedicated to the methodology for performing ontology matching. It also covers emerging topics, such as data interlinking, ontology partitioning and pruning, context-based matching, matcher tuning, alignment debugging, and user involvement in matching, to mention a few. More than 100 state-of-the-art matching systems and frameworks were reviewed. With Ontology Matching, researchers and practitioners will find a reference book that presents currently available work in a uniform framework. In particular, the work and the techniques presented in this book can be equally applied to database schema matching, catalog integration, XML schema matching and other related problems. The objectives of the book include presenting (i) the state of the art and (ii) the latest research results in ontology matching by providing a systematic and detailed account of matching techniques and matching systems from theoretical, practical and application perspectives.

Ontology Matching

Intramuscular fat (IMF) content plays a key role in various quality traits of meat. IMF content varies between species, between breeds and between muscle types in the same breed. Other factors are involved in the variation of IMF content in animals, including gender, age and feeding. Variability in IMF content is mainly linked to the number and size of intramuscular adipocytes. The accretion rate of IMF depends on the muscle growth rate. For instance, animals having a high muscularity with a high glycolytic activity display a reduced development of IMF. This suggests that muscle cells and adipocytes interplay during growth. In addition, early events that influence adipogenesis inside the muscle (i.e proliferation and differentiation of adipose cells, the connective structure embedding adipocytes) might be involved in interindividual differences in IMF content. Increasing muscularity will also dilute the final fat content of muscle. At the metabolic level, IMF content results from the balance between uptake, synthesis and degradation of triacylglycerols, which involve many metabolic pathways in both adipocytes and myofibres. Various experiments revealed an association between IMF level and the muscle content in adipocyte-type fatty acid-binding protein, the activities of oxidative enzymes, or the delta-6-desaturase level; however, other studies failed to confirm such relationships. This might be due to the importance of fatty acid fluxes that is likely to be responsible for variability in IMF content during the postnatal period rather than the control of one single pathway. This is evident in the muscle of most fish species in which triacylglycerol synthesis is almost zero. Genetic approaches for increasing IMF have been focused on live animal ultrasound to derive estimated breeding values. More recently, efforts have concentrated on discovering DNA markers that change the distribution of fat in the body (i.e. towards IMF at the expense of the carcass fatness). Thanks to the exhaustive nature of genomics (transcriptomics and proteomics), our knowledge on fat accumulation in muscles is now being underpinned. Metabolic specificities of intramuscular adipocytes have also been demonstrated, as compared to other depots. Nutritional manipulation of IMF independently from body fat depots has proved to be more difficult to achieve than genetic strategies to have lipid deposition dependent of adipose tissue location. In addition, the biological mechanisms that explain the variability of IMF content differ between genetic and nutritional factors. The nutritional regulation of IMF also differs between ruminants, monogastrics and fish due to their digestive and nutritional particularities.

https://researchrepository.murdoch.edu.au/6455/1/fat_content_in_meat%2Dproducing_animals.pdf

Intramuscular fat content in meat-producing animals: development, genetic and nutritional control, and identification of putative markers.

This paper studies methods of quantitatively measuring semantic information in communication. We review existing work on quantifying semantic information, then investigate a model-theoretical approach for semantic data compression and reliable semantic communication. We relate our approach to the statistical measurement of information by Shannon, and show that Shannon's source and channel coding theorems have semantic counterparts.

Towards a theory of semantic communication

In many data-centric semantic web applications, it is desirable to use OWL to encode the Integrity Constraints (IC) that must be satisfied by instance data. However, challenges arise due to the Open World Assumption (OWA) and the lack of a Unique Name Assumption (UNA) in OWL's standard semantics. In particular, conditions that trigger constraint violations in systems using the Closed World Assumption (CWA), will generate new inferences in standard OWL-based reasoning applications. In this paper, we present an alternative IC semantics for OWL that allows applications to work with the CWA and the weak UNA. Ontology modelers can choose which OWL axioms to be interpreted with our IC semantics. Thus application developers are able to combine open world reasoning with closed world constraint validation in a flexible way. We also show that IC validation can be reduced to query answering under certain conditions. Finally, we describe our prototype implementation based on the OWL reasoner Pellet.

https://www.aaai.org/ocs/index.php/AAAI/AAAI10/paper/download/1931/2229

Integrity constraints in OWL

Query formulation is a key aspect of information retrieval, contributing to both the efficiency and usability of many semantic applications. A number of query languages, such as SPARQL, have been developed for the Semantic Web; however, there are, as yet, few tools to support end users with respect to the creation and editing of semantic queries. In this paper we introduce NITELIGHT, a Web-based graphical tool for semantic query construction that is based on the W3C SPARQL specification. NITELIGHT combines a number of features to support end-users with respect to the creation of SPARQL queries. These include a columnar ontology browser, an interactive graphical design surface, a SPARQL-compliant visual query language, a SPARQL syntax viewer and an integrated semantic query results browser. The functionality of each of these components is described in the current paper. In addition, we discuss the potential contribution of the NITELIGHT tool to rule creation/editing and semantic integration capabilities.

/pdf/a-visual-approach-to-semantic-query-design-using-a-web-based-lgo2t4dqju.pdf

A Visual Approach to Semantic Query Design Using a Web-Based Graphical Query Designer

Modular ontology languages, such as Distributed Description Logics (DDL), $\mathcal{E}$-connections and Package-based Description Logics (P-DL) offer two broad classes of approaches to connect multiple ontology modules: the use of mappings or linkings between ontology modules e.g., DDL and $\mathcal{E}$-connections; and the use of importing e.g., P-DL. The major difference between the two approaches is on the usage of “foreign terms” at the syntactic level, and on the local model disjointness at the semantic level. We compare the semantics of linking in DDL and $\mathcal{E}$-connections, and importing in P-DL within the Distributed First Order Logics (DFOL) framework. Our investigation shows that the domain disjointness assumption adopted by the linking approach leads to several semantic difficulties. We explore the possibility of avoiding some of these difficulties using the importing approach to linking ontology modules.

/pdf/on-the-semantics-of-linking-and-importing-in-modular-4wmqo547lk.pdf

On the semantics of linking and importing in modular ontologies

We present the syntax and semantics of a family of modular ontology languages, Package-based Description Logics (P-DL), to support context- specific reuse of knowledge from multiple ontology modules. In particular, we describe a P-DL ${\mathcal SHOIQP}$ that allows the importing of concept, role and nominal names between multiple ontology modules (each of which can be viewed as a ${\mathcal SHOIQ}$ ontology). ${\mathcal SHOIQP}$ supports contextualized interpretation, i.e., interpretation from the point of view of a specific package. We establish the necessary and sufficient conditions on domain relations (i.e., the relations between individuals in different local domains) that need to hold in order to preserve the unsatisfiability of concept formulae, monotonicity of inference, transitive reuse of knowledge across modules.

/pdf/package-based-description-logics-5bo1tprppb.pdf

Jie Bao

Papers

Towards a theory of semantic communication

Integrity constraints in OWL

A Visual Approach to Semantic Query Design Using a Web-Based Graphical Query Designer

On the semantics of linking and importing in modular ontologies

Package-Based Description Logics