Search Constraints
Number of results to display per page
Results for:
Polyu oer sim
No
Remove constraint Polyu oer sim: No
Search Results
-
Others
Extract human-understandable insights from any machine learning model.
- Subjects:
- Computing
- Keywords:
- Python (Computer program language) Machine learning
- Resource Type:
- Others
-
e-book
Machine learning techniques have the potential of alleviating the complexity of knowledge acquisition. This book presents today’s state and development tendencies of machine learning. It is a multi-author book. Taking into account the large amount of knowledge about machine learning and practice presented in the book, it is divided into three major parts: Introduction, Machine Learning Theory and Applications. Part I focuses on the introduction to machine learning. The author also attempts to promote a new design of thinking machines and development philosophy. Considering the growing complexity and serious difficulties of information processing in machine learning, in Part II of the book, the theoretical foundations of machine learning are considered, and they mainly include self-organizing maps (SOMs), clustering, artificial neural networks, nonlinear control, fuzzy system and knowledge-based system (KBS). Part III contains selected applications of various machine learning approaches, from flight delays, network intrusion, immune system, ship design to CT and RNA target prediction. The book will be of interest to industrial engineers and scientists as well as academics who wish to pursue machine learning. The book is intended for both graduate and postgraduate students in fields such as computer science, cybernetics, system sciences, engineering, statistics, and social sciences, and as a reference for software professionals and practitioners.
- Course related:
- COMP4432 Machine Learning
- Subjects:
- Computing
- Keywords:
- Machine learning
- Resource Type:
- e-book
-
Presentation
This video was recorded at 7th Extended Semantic Web Conference (ESWC), Heraklion 2010. The mission of the Extended Semantic Web Conference (ESWC 2010) is to bring together researchers and practioners dealing with different aspects of semantics on the Web. ESWC2010 builds on the success of the former European Semantic Web Conference series, but seeks to extend its focus by engaging with other communities within and outside ICT, in which semantics can play an important role. At the same time, ESWC2010 is a truly international conference. Semantics of web content, enriched with domain theories (ontologies), data about web usage, natural language processing, etc. will enable a web that provides a qualitatively new level of functionality. It will weave together a large network of human knowledge and make this knowledge machine-processable. Various automated services, based on reasoning with metadata and ontologies, will help the users to achieve their goals by accessing and processing information in machine-understandable form. This network of knowledge systems will ultimately lead to truly intelligent systems, which will be employed for various complex decision-making tasks. Research about web semantics can benefit from ideas and cross-fertilization with many other areas: Artificial Intelligence, Natural Language Processing, Database and Information Systems, Information Retrieval, Multimedia, Distributed Systems, Social Networks, Web Engineering, and Web Science. ESWC2010 will present the latest results in research and applications in its field. The research program will be organised in targeted tracks. In addition, the conference will feature a tutorial program, system descriptions and demos, a posters track, a Ph.D. symposium and a number of collocated workshops. The calls for these events are separate and can be found on the conference Web site (http://www.eswc2010.org/).
- Subjects:
- Management and Computing
- Keywords:
- Industrial management Workflow -- Management
- Resource Type:
- Presentation
-
Presentation
This video was recorded at 11th International Semantic Web Conference (ISWC), Boston 2012. The New York Times committment to Linked Data began over 160 years ago. Starting in 1851, The New York Times has always catalogued its archival articles using a controlled vocabulary of people, places, organizations and descriptors. In 2009 The New York Times started publishing this vocabulary as linked data using semantic web standards. In 2011 The Times announced the launch of several RESTful Semantic APIs. And in late 2012 and early 2013, The Times will migrate its entire process for vocabulary management to a system designed around the principles of Linked Data. In my remarks, I will survey the history of Semantic publishing at The New York Times, outline our semantic strategy, detail the business-case for linked data at The Times and provide an in-depth explanation of our new vocabulary management system.
- Subjects:
- Management and Computing
- Keywords:
- Linked data New York times
- Resource Type:
- Presentation
-
Presentation
This video was recorded at COIN / PlanetData Winter School on Knowledge Technologies for Complex Business Environments, Ljubljana 2011. Organized by COIN FP7 Integrated Project and PlanetData FP7 Network of Excellence, the school seeks to bring together students, scholars and researchers from industry in order to foster collaboration and interoperability with innovative services and project large-scale data management in business environments. The main topics of the winter school are: Interoperability and collaboration models and solutions, Enterprise interoperability and collaboration services, Innovative knowledge and semantically powered technologies, Knowledge process and context modelling, Pro-active knowledge tools, Large scale analytics and reasoning tools, Business cases and real case studies.
- Subjects:
- Management and Computing
- Keywords:
- Linked data Application program interfaces (Computer software)
- Resource Type:
- Presentation
-
Others
Kaggle offers a no-setup, customizable, Jupyter Notebooks environment. Access GPUs at no cost to you and a huge repository of community published data & code. Inside Kaggle you’ll find all the code & data you need to do your data science work. Use over 50,000 public datasets and 400,000 public notebooks to conquer any analysis in no time.
- Subjects:
- Computing
- Keywords:
- Machine learning Artificial intelligence Big data
- Resource Type:
- Others
-
Others
A dataset of five actors performing five different actions (drink, eat, jump, run and walk) on a treadmill from five different views (0, 45, 90, 135, and 180 degrees from the front of the actor/treadmill; the treadmill rather than the camera was rotated in place to acquire from different viewpoints). The dataset was filmed on a fixed, constant background.
- Subjects:
- Computing
- Keywords:
- Motion perception (Vision) Computer vision Optical pattern recognition
- Resource Type:
- Others
-
Courseware
This is an accelerated introduction to MATLAB® and its popular toolboxes. Lectures are interactive, with students conducting sample MATLAB problems in real time. The course includes problem-based MATLAB assignments. Students must provide their own laptop and software. This is great preparation for classes that use MATLAB.
- Subjects:
- Computing
- Keywords:
- Engineering mathematics -- Data processing MATLAB Numerical analysis -- Computer programs
- Resource Type:
- Courseware
-
Courseware
This course is an introduction to the theory and practice of the process of designing games and playful experiences. Students are familiarized with methods, concepts, techniques, and literature used in the design of games. The strategy is process-oriented, focusing on aspects such as: Rapid prototyping, play testing, and design iteration using a player-centered approach.
- Subjects:
- Interactive and Digital Media and Computing
- Keywords:
- Games
- Resource Type:
- Courseware
-
Courseware
Broadly speaking, functional programming is a style of programming in which the primary method of computation is the application of functions to arguments. Among other features, functional languages offer a compact notation for writing programs, powerful abstraction methods for structuring programs, and a simple mathematical basis that supports reasoning about programs. Functional languages represent the leading edge of programming language design, and the primary setting in which new programming concepts are introduced and studied. All contemporary programming languages such as Hack/PHP, C#, Visual Basic, F#, C++, JavaScript, Python, Ruby, Java, Scala, Clojure, Groovy, Racket, … support higher-order programming via the concept of closures or lambda expressions. This course will use Haskell as the medium for understanding the basic principles of functional programming. While the specific language isn’t all that important, Haskell is a pure functional language so it is entirely appropriate for learning the essential ingredients of programming using mathematical functions. It is also a relatively small language, and hence it should be easy for you to get up to speed with Haskell. Once you understand the Why, What and How that underlies pure functional programming and learned to “think like a fundamentalist”, we will apply the concepts of functional programming to “code like a hacker” in mainstream programming languages, using Facebook’s novel Hack language as our main example. This course assumes no prior knowledge of functional programming, but assumes you have at least one year of programming experience in a regular programming language such as Java, .NET, Javascript or PHP.
- Subjects:
- Computing
- Keywords:
- Haskell (Computer program language) Functional programming (Computer science)
- Resource Type:
- Courseware