Ontologies


Learning a Concept Hierarchy from Multi-labeled Documents

Neural Information Processing Systems

While topic models can discover patterns of word usage in large corpora, it is difficult to meld this unsupervised structure with noisy, human-provided labels, especially when the label space is large. In this paper, we present a model-Label to Hierarchy (L2H)-that can induce a hierarchy of user-generated labels and the topics associated with those labels from a set of multi-labeled documents. The model is robust enough to account for missing labels from untrained, disparate annotators and provide an interpretable summary of an otherwise unwieldy label set. We show empirically the effectiveness of L2H in predicting held-out words and labels for unseen documents. Papers published at the Neural Information Processing Systems Conference.


Mapping paradigm ontologies to and from the brain

Neural Information Processing Systems

Due to the nature of the individual experiments, based on eliciting neural response from a small number of stimuli, this link is incomplete, and unidirectional from the causal point of view. To come to conclusions on the function implied by the activation of brain regions, it is necessary to combine a wide exploration of the various brain functions and some inversion of the statistical inference. Here we introduce a methodology for accumulating knowledge towards a bidirectional link between observed brain activity and the corresponding function. We rely on a large corpus of imaging studies and a predictive engine. Technically, the challenges are to find commonality between the studies without denaturing the richness of the corpus.


An Introduction to Artificial Intelligence Applied to Multimedia

#artificialintelligence

In this chapter, we give an introduction to symbolic artificial intelligence (AI) and discuss its relation and application to multimedia. We begin by defining what symbolic AI is, what distinguishes it from non-symbolic approaches, such as machine learning, and how it can used in the construction of advanced multimedia applications. We then introduce description logic (DL) and use it to discuss symbolic representation and reasoning. DL is the logical underpinning of OWL, the most successful family of ontology languages. After discussing DL, we present OWL and related Semantic Web technologies, such as RDF and SPARQL.


Metadata Management for the Machinery Industry - PoolParty News

#artificialintelligence

Vienna, November 19th of 2019, Semantic Web Company (Austria) and PANTOPIX (Germany) have announced a comprehensive cooperation to provide the machinery industry with expertise in metadata management and structured information. Semantic Web Company (SWC), based in Vienna, is the leading provider of graph-based metadata management. The Germany Company PANTOPIX is a high-end specialist for improving information processes, developing data models as well as providing intelligent information for technical documentation. The key pillar of the partnership is to develop taxonomies, ontologies and large-scale Enterprise Knowledge Graphs to make target-oriented technical content available to internal and external customers. Knowledge Graphs enable companies to process large amounts of data from various silos and adding value to it so that it can be used in meaningful and more intelligent ways.


ML and DL Libraries Performance Optimization

#artificialintelligence

One of Auriga's goals is establishing long-term trustful partnerships with its customers, some of which effectively evolve through decades.


Using SLX FPGA For Performance Optimization Of SHA-3 For HLS

#artificialintelligence

Leveraging standard HLS (High Level Synthesis) tools from FPGA vendors, SLX FPGA tackles the challenges associated with the HLS design flow. In this paper, the results of an SLX FPGA-optimized implementation of a Secure Hash Algorithm (SHA-3; also known as Keccak) are compared to a competition-winning hand-optimized HLS implementation of the same algorithm. SLX provides a nearly 400x speed-up over the unoptimized implementation and even outperforms the hand-optimized implementation by 14%. Moreover, it is also more resource efficient, consuming nearly 3.6 times less look-up tables and 1.76 times less flip-flops. Click here to read more.


Ontology Meetup - FoundersList

#artificialintelligence

Please join the Ontology team as they tour the United States presenting their solution for a public blockchain & distributed collaboration platform. They will discuss their unique viewpoint on developing blockchain technology in China & its impact throughout the space. He is one of the first Semantic Web experts in China & has many years of experience in enterprise resource planning, digitization of government affairs, gaming platforms, & media streaming. In 2008, he joined Project Halo, a project initiated by Paul Allen, Co-Founder of Microsoft, where he worked on big data & artificial intelligence. In 2013, Hu helped set up leading fintech company Green Dot's subsidiary in China, where he developed a thorough understanding of the financial system & credit card business.


ARGO - the Amazon Rainforest Genome Ontology project.

#artificialintelligence

ARGO is short for the Amazon Rainforest Genome Ontology project. The mission is to tap into the scientific, biotechnological, and medical potential of the plant biodiversity in the Amazon rainforest in order to discover, utilise and preserve their biological value … before it is too late. If you want to follow our progress, please signup below.


Is it a Fruit, an Apple or a Granny Smith? Predicting the Basic Level in a Concept Hierarchy

arXiv.org Artificial Intelligence

Is it a Fruit, an Apple or a Granny Smith? Abstract The "basic level", according to experiments in cognitive psychology, is the level of abstraction in a hierarchy of concepts at which humans perform tasks quicker and with greater accuracy than at other levels. We argue that applications that use concept hierarchies - such as knowledge graphs, ontologies or taxonomies - could significantly improve their user interfaces if they'knew' which concepts are the basic level concepts. This paper examines to what extent the basic level can be learned from data. We test the utility of three types of concept features, that were inspired by the basic level theory: lexical features, structural features and frequency features. We evaluate our approach on WordNet, and create a training set of manually labelled examples that includes concepts from different domains. Our findings include that the basic level concepts can be accurately identified within one domain. Concepts that are difficult to label for humans are also harder to classify automatically. Our experiments provide insight into how classification performance across domains could be improved, which is necessary for identification of basic level concepts on a larger scale. 1 Introduction One of the ongoing challenges in Artificial Intelligence is to explicitly describe the world in ways that machines can process. This has resulted in taxonomies, thesauri, ontologies and more recently knowledge graphs. While these various knowledge organization systems (KOSs) may use different formal languages, they all share similar underlying data representations.