Intelligent Systems: Three Practical Questions. Carsten Rother

Size: px
Start display at page:

Download "Intelligent Systems: Three Practical Questions. Carsten Rother"

Transcription

1 Intelligent Systems: Three Practical Questions Carsten Rother 04/02/2015

2 Prüfungsfragen Nur vom zweiten Teil der Vorlesung (Dimitri Schlesinger, Carsten Rother) Drei Typen von Aufgaben: 1) Algorithmen 2) Definitionen und Wissensfragen 3) Theoretische Herleitungen Fragen werden auf Deutsch gestellt 04/02/2015 2

3 1) Algorithmen Was würde ein parallelisierter ICM Algorithmus in den nächsten zwei Schritten machen? Bitte zeichnen sie ein. Gegeben die Energy: x 1 x 2 Initializer Zustand: x 1 =0 x 2 =1 Hinweis: dunkle Konten werden im ersten Schritt nicht verändert x 4 x 3 x 4 =0 x 3 = 1 x i {0,1} θ 1 0 = 0, θ 1 1 = 1 θ 2 0 = 1, θ 2 1 = 1 θ 3 0 = 2, θ 3 1 = 1 θ 4 0 = 1, θ 4 1 = 2 θ ij x i, x j = x i x j For all i, j Schritt 1: x 1 =? x 2 =? x 4 =? x 3 =? Schritt 2: x 1 =? x 2 =? x 4 =? x 3 =? 04/02/2015 3

4 2) Definitionen und Wissensfragen Frage: Was ist ein strukturiertes Model ( structured model )? Antwort: Ein Modell in dem die Ausgaben nicht unabhängig sind. Der Zusammenhang der Ausgaben wird modelliert. 04/02/2015 4

5 3) Theoretische Herleitungen Man berechne die Wahrscheinlichkeit dafür, dass die Summe der Augenzahlen zweier voneinander unabhängig gewürfelten Spielwürfel durch 5 teilbar ist. (ähnliche Aufgaben wurden in der Vorlesung und Übung betrachtet) 04/02/2015 5

6 Roadmap this lecture The question of the combinatorial explosion The question of generalization The questions with Big Data 04/02/2015 6

7 Roadmap this lecture The question of the combinatorial explosion The question of generalization The questions with Big Data 04/02/2015 7

8 Going back to 1973 Sir James Lighthill report to the British Parliament The general purpose robot is a mirage Ein Roboter der alles kann ist eine Illusion Full report on Youtube: 04/02/2015 8

9 Going back to 1973 Sir James Lighthill report to the British Parliament He specifically mentioned the problem of "combinatorial explosion" or "intractability", which implied that many of AI's most successful algorithms would grind to a halt on real world problems and were only suitable for solving "toy" tasks. 04/02/2015 9

10 (My) View: 2015 Better computers (faster, more memory, clusters, GPUs) More powerful methods which can deal with combinatorial exploration (e.g. graph cut, search) Better sensors (e.g. time-of-flight) More (labeled) data can give better, more adaptive methods (e.g. deep learning) Humans can do it, and they have a finite-sized brain. 04/02/

11 Roadmap this lecture The question of the combinatorial explosion The question of generalization The questions with Big Data 04/02/

12 Mushroom example Measure attributes: - Size in centimeters - Color: Average whitness of the whole mushroom, e.g. diagonal in RGB cube 15cm Size 2cm 0 white 255 Task: Build a decision tree such that you can distgunish form mushrooms. 04/02/

13 Decision Tree Size>8cm 15cm Size 2cm 0 white /02/

14 Decision Tree Size>8cm white>180 15cm Size 2cm 0 white /02/

15 Decision Tree Split Criteria Before split Split 1 Split 2 Information gain Shannon s entropy Think of minimizing Entropy 04/02/

16 Decision Tree Split Criteria We have S = 12 with S L = 6 and S R = 6 In S we have 6 red and 6 blue points (2 classes) H(S) = 0.5 log log 0.5 = 1 We look at two possible splits: 1) 50%-50% class-split (each side (S L and S R ) gets 3 red and 3 blue) H S L = 0.5 log log 0.5 = 1 H S R = 0.5 log log 0.5 = 1 I(S) = H(S) ( ) = H(S) 1 = 0 (Lower information gain) 2) 16%-84% class-split (left side has 5 red and 1 blue, right side has 5 blue and 1 red) H S L = 1 log log 5 = H S R = 1 log log 5 = I S = H S = H S 0.64 = 0.36 (Higher information gain) 04/02/

17 Generalization Training Data: Test Data: Size>8cm white>180 System is optimal! 04/02/

18 Generalization Training Data: Test Data: Size>8cm white>180 System may be optimal! 04/02/

19 Generalization 15cm Size 2cm white BUT its BUT its!! 04/02/

20 Definition Over-fitting: Is the effect that the model perfectly memorizes the training data, but does perform well on test data Generalization: One of the most important aspect of a model is its ability to generalize. That means that new (unseen) test data is correctly classified. A model which overfitts does generalize well. How to avoid over-fitting? Idea 1: Max-Margin Idea 2: Do make the trees too deep 04/02/

21 Max-Margin Size>9cm white>190 15cm Size 2cm 0 white 255 Place decision boundary such that the distance to all (some) examples is maximized! 04/02/

22 Do make the trees too deep Size>9cm 15cm Output: p() = 2/3 p( ) = 1/3 Size 2cm 0 white /02/

23 Do make the trees too deep - Comparison Test data: 15cm Not Size System with 2 nodes makes: 2 mistakes on test data System with 1 nodes makes: 2 mistakes on test data 2cm Not 0 white 255 This means: system with one node makes a mistake during training, but performs equally well on testing phase. 04/02/

24 Example: People tracking body joint hypotheses input depth image body parts Bodypart Labelling Clustering Body is divided into 31 body parts (simple centroid computation) front view side view top view 04/02/

25 Small Model capacity Model Is the part round? Is it darker below me? Color red Test time: Training data 04/02/

26 Large Model capacity Model Is the part round? Is it darker below me? Tree is very deep (e.g. depth 30) Is the colour of my pixel 130? Test time: Training data The Model perfectly memorizes the training data! 04/02/

27 Tree Depth More training data pushes this boundary Number of Parameters (tree depth) Decision trees 04/02/

28 Infinite Training Data Model Is the colour of my pixel 130? Is the colour of my pixel 131? Tree is very deep (e.g. depth 30) The Model perfectly memorizes the training data! Test time: If we were to have all possible training images that can occur (inclusive noise) 04/02/

29 Real System that runs on Xbox! accuracy Amount of Training Data is one of the main factors 04/02/

30 Roadmap this lecture The question of the combinatorial explosion The question of generalization The questions with Big Data 04/02/

31 The important factors Model Power Performance (e.g. tree depth) Training Data (unlabeled and labeled!) More Training Data = More powerful models = Better Performance 04/02/

32 The Increase in Data 2014 ~10M images ~60M Parameters accuracy rate: ~85% ImageNet Challenge 2005 ~100 training images ~100 Parameters accuracy rate: ~20% 04/02/

33 Deep Models have many parameters The return of Neural Networks from the ~70s made them work Major leap forward in ImageNet Challenge [ImageNet Classification with Deep Convolutional Neural Networks, Hinton et al. 2013] 04/02/

34 Where does the training Data come from? 1. Anation by researchers: ~1K training images 2. Search Engines: type in cow 3. Crowd sourcing: ~1M training images 4. Simulation: ~10M training images 04/02/

35 Where does the training Data come from? 1. Get images of tigers 2. Search Engines: type in tiger 3. Crowd sourcing: run e.g. Amazon Mechanical Turk to filter out bad images. (Start-up companies) 04/02/

36 Where does the training Data come from? ImageNet challenge 1.2 Million anated images; classes 04/02/

37 Where does the training Data come from Simulation: ~10M training images Record mocap 100,000s of poses Retarget to varied body shapes [Vicon] Render (depth, body parts) pairs + add noise we start to look into this with biologists 04/02/

38 Roadmap this lecture The question of the combinatorial explosion The question of generalization The questions with Big Data 04/02/

39 Thanks! 04/02/

Contents. What is Wirtschaftsmathematik?

Contents. What is Wirtschaftsmathematik? Contents. Introduction Modeling cycle SchokoLeb example Graphical procedure Standard-Form of Linear Program Vorlesung, Lineare Optimierung, Sommersemester 04 Page What is Wirtschaftsmathematik? Using mathematical

More information

Machine Learning. Chapter 18, 21. Some material adopted from notes by Chuck Dyer

Machine Learning. Chapter 18, 21. Some material adopted from notes by Chuck Dyer Machine Learning Chapter 18, 21 Some material adopted from notes by Chuck Dyer What is learning? Learning denotes changes in a system that... enable a system to do the same task more efficiently the next

More information

INSRUCTION MANUAL AND GUARANTEE POLICY

INSRUCTION MANUAL AND GUARANTEE POLICY INSRUCTION MANUAL AND GUARANTEE POLICY FRACTOMETER II made in Germany by: IML- Instrumenta Mechanik Labor GmbH Großer Stadtacker 2 69168 Wiesloch Germany Phone: (+49) 6222 / 6797-0 Fax: (+49) 6222-6797-

More information

An Introduction to Data Mining. Big Data World. Related Fields and Disciplines. What is Data Mining? 2/12/2015

An Introduction to Data Mining. Big Data World. Related Fields and Disciplines. What is Data Mining? 2/12/2015 An Introduction to Data Mining for Wind Power Management Spring 2015 Big Data World Every minute: Google receives over 4 million search queries Facebook users share almost 2.5 million pieces of content

More information

Microsoft Certified IT Professional (MCITP) MCTS: Windows 7, Configuration (070-680)

Microsoft Certified IT Professional (MCITP) MCTS: Windows 7, Configuration (070-680) Microsoft Office Specialist Office 2010 Specialist Expert Master Eines dieser Examen/One of these exams: Eines dieser Examen/One of these exams: Pflichtexamen/Compulsory exam: Word Core (Exam 077-881)

More information

Machine Learning: Overview

Machine Learning: Overview Machine Learning: Overview Why Learning? Learning is a core of property of being intelligent. Hence Machine learning is a core subarea of Artificial Intelligence. There is a need for programs to behave

More information

Information Systems 2

Information Systems 2 Information Systems 2 Prof. Dr. Dr. L. Schmidt-Thieme MSc. André Busche Übung 9 0. Allerlei 1. Übung 2. Hands on some things 2.1 Saxon 2.2 Corba 28.06.10 2/ 0. Allerlei 1. Übung 2. Hands on some things

More information

Mit einem Auge auf den mathema/schen Horizont: Was der Lehrer braucht für die Zukun= seiner Schüler

Mit einem Auge auf den mathema/schen Horizont: Was der Lehrer braucht für die Zukun= seiner Schüler Mit einem Auge auf den mathema/schen Horizont: Was der Lehrer braucht für die Zukun= seiner Schüler Deborah Löwenberg Ball und Hyman Bass University of Michigan U.S.A. 43. Jahrestagung für DidakEk der

More information

CORPORATE DESIGN MANUAL English 5/2015

CORPORATE DESIGN MANUAL English 5/2015 CORPORATE DESIGN MANUAL English 5/2015 CONTENT Corporate Design Manual Introduction and contact 3 1 Name and logo 4 2 Label 6 3 Fonts 10 4 Colours 11 2 INTRODUCTION Introduction This corporate design manual

More information

Introduction to Machine Learning Lecture 1. Mehryar Mohri Courant Institute and Google Research mohri@cims.nyu.edu

Introduction to Machine Learning Lecture 1. Mehryar Mohri Courant Institute and Google Research mohri@cims.nyu.edu Introduction to Machine Learning Lecture 1 Mehryar Mohri Courant Institute and Google Research mohri@cims.nyu.edu Introduction Logistics Prerequisites: basics concepts needed in probability and statistics

More information

Dynamic Pricing and Automated Resource Allocation for Complex Information Services

Dynamic Pricing and Automated Resource Allocation for Complex Information Services Lecture Notes in Economics and Mathematical Systems 589 Dynamic Pricing and Automated Resource Allocation for Complex Information Services Reinforcement Learning and Combinatorial Auctions Bearbeitet von

More information

Learning Example. Machine learning and our focus. Another Example. An example: data (loan application) The data and the goal

Learning Example. Machine learning and our focus. Another Example. An example: data (loan application) The data and the goal Learning Example Chapter 18: Learning from Examples 22c:145 An emergency room in a hospital measures 17 variables (e.g., blood pressure, age, etc) of newly admitted patients. A decision is needed: whether

More information

ida.com excellence in dependable automation

ida.com excellence in dependable automation IEC 61508 Maintenance Status IEC 61508 Maintenance Projekt ist aus dem zulässigen Zeitrahmen gelaufen Viele Baustellen auch durch neue Mitglieder (Frankreich, USA, IEC 61511 Team) Bestehende Anforderungen,

More information

Introduction to Learning & Decision Trees

Introduction to Learning & Decision Trees Artificial Intelligence: Representation and Problem Solving 5-38 April 0, 2007 Introduction to Learning & Decision Trees Learning and Decision Trees to learning What is learning? - more than just memorizing

More information

COMP3420: Advanced Databases and Data Mining. Classification and prediction: Introduction and Decision Tree Induction

COMP3420: Advanced Databases and Data Mining. Classification and prediction: Introduction and Decision Tree Induction COMP3420: Advanced Databases and Data Mining Classification and prediction: Introduction and Decision Tree Induction Lecture outline Classification versus prediction Classification A two step process Supervised

More information

A: Ein ganz normaler Prozess B: Best Practices in BPMN 1.x. ITAB / IT Architekturbüro Rüdiger Molle März 2009

A: Ein ganz normaler Prozess B: Best Practices in BPMN 1.x. ITAB / IT Architekturbüro Rüdiger Molle März 2009 A: Ein ganz normaler Prozess B: Best Practices in BPMN 1.x ITAB / IT Architekturbüro Rüdiger Molle März 2009 März 2009 I T A B 2 Lessons learned Beschreibung eines GP durch das Business läßt Fragen der

More information

CI6227: Data Mining. Lesson 11b: Ensemble Learning. Data Analytics Department, Institute for Infocomm Research, A*STAR, Singapore.

CI6227: Data Mining. Lesson 11b: Ensemble Learning. Data Analytics Department, Institute for Infocomm Research, A*STAR, Singapore. CI6227: Data Mining Lesson 11b: Ensemble Learning Sinno Jialin PAN Data Analytics Department, Institute for Infocomm Research, A*STAR, Singapore Acknowledgements: slides are adapted from the lecture notes

More information

131-1. Adding New Level in KDD to Make the Web Usage Mining More Efficient. Abstract. 1. Introduction [1]. 1/10

131-1. Adding New Level in KDD to Make the Web Usage Mining More Efficient. Abstract. 1. Introduction [1]. 1/10 1/10 131-1 Adding New Level in KDD to Make the Web Usage Mining More Efficient Mohammad Ala a AL_Hamami PHD Student, Lecturer m_ah_1@yahoocom Soukaena Hassan Hashem PHD Student, Lecturer soukaena_hassan@yahoocom

More information

Data Mining Cluster Analysis: Basic Concepts and Algorithms. Lecture Notes for Chapter 8. Introduction to Data Mining

Data Mining Cluster Analysis: Basic Concepts and Algorithms. Lecture Notes for Chapter 8. Introduction to Data Mining Data Mining Cluster Analysis: Basic Concepts and Algorithms Lecture Notes for Chapter 8 Introduction to Data Mining by Tan, Steinbach, Kumar Tan,Steinbach, Kumar Introduction to Data Mining 4/8/2004 Hierarchical

More information

AP WORLD LANGUAGE AND CULTURE EXAMS 2012 SCORING GUIDELINES

AP WORLD LANGUAGE AND CULTURE EXAMS 2012 SCORING GUIDELINES AP WORLD LANGUAGE AND CULTURE EXAMS 2012 SCORING GUIDELINES Interpersonal Writing: E-mail Reply 5: STRONG performance in Interpersonal Writing Maintains the exchange with a response that is clearly appropriate

More information

Data Mining Classification: Decision Trees

Data Mining Classification: Decision Trees Data Mining Classification: Decision Trees Classification Decision Trees: what they are and how they work Hunt s (TDIDT) algorithm How to select the best split How to handle Inconsistent data Continuous

More information

Get Related Schatzsuche in SciFinder Scholar

Get Related Schatzsuche in SciFinder Scholar Get Related Schatzsuche in SciFinder Scholar Schatzsuche in Dokumenten Get related zitierende Schriften (ab 1999 *) Get related zitierte Schriften (ab 1907) Get related Substances! NEU in 2002 Get related

More information

Diese Liste wird präsentiert von. Netheweb.de

Diese Liste wird präsentiert von. Netheweb.de Diese Liste wird präsentiert von Netheweb.de Die Liste enthält 1000 Do-Follow Blogs, die zum Linkbuilding genutzt werden können, es kann sein, dass verkürzte URL s nicht korrekt weiter geleitet werden.

More information

Search Engines Chapter 2 Architecture. 14.4.2011 Felix Naumann

Search Engines Chapter 2 Architecture. 14.4.2011 Felix Naumann Search Engines Chapter 2 Architecture 14.4.2011 Felix Naumann Overview 2 Basic Building Blocks Indexing Text Acquisition Text Transformation Index Creation Querying User Interaction Ranking Evaluation

More information

Machine Learning. CS 188: Artificial Intelligence Naïve Bayes. Example: Digit Recognition. Other Classification Tasks

Machine Learning. CS 188: Artificial Intelligence Naïve Bayes. Example: Digit Recognition. Other Classification Tasks CS 188: Artificial Intelligence Naïve Bayes Machine Learning Up until now: how use a model to make optimal decisions Machine learning: how to acquire a model from data / experience Learning parameters

More information

Data Mining. Nonlinear Classification

Data Mining. Nonlinear Classification Data Mining Unit # 6 Sajjad Haider Fall 2014 1 Nonlinear Classification Classes may not be separable by a linear boundary Suppose we randomly generate a data set as follows: X has range between 0 to 15

More information

Cloud OS Network. Uwe Lüthy, Die Bedeutung einer Partner Managed Cloud für Kunden. Partner Technology Strategiest uwelu@microsoft.

Cloud OS Network. Uwe Lüthy, Die Bedeutung einer Partner Managed Cloud für Kunden. Partner Technology Strategiest uwelu@microsoft. Cloud OS Network Die Bedeutung einer Partner Managed Cloud für Kunden. Uwe Lüthy, Partner Technology Strategiest uwelu@microsoft.com Die Cloud Opportunity Definition von Buzzwords Cloud OS Strategie Wichtig

More information

Artificial Neural Networks and Support Vector Machines. CS 486/686: Introduction to Artificial Intelligence

Artificial Neural Networks and Support Vector Machines. CS 486/686: Introduction to Artificial Intelligence Artificial Neural Networks and Support Vector Machines CS 486/686: Introduction to Artificial Intelligence 1 Outline What is a Neural Network? - Perceptron learners - Multi-layer networks What is a Support

More information

I Textarbeit. Text 1. I never leave my horse

I Textarbeit. Text 1. I never leave my horse BEJ Musterprüfung Englisch (11020) 1 I Textarbeit Text 1 I never leave my horse 1 5 10 15 20 Police officers in Ireland don t carry guns. But they often ride through Dublin on horses. Julie Folan is a

More information

Foundations of Artificial Intelligence. Introduction to Data Mining

Foundations of Artificial Intelligence. Introduction to Data Mining Foundations of Artificial Intelligence Introduction to Data Mining Objectives Data Mining Introduce a range of data mining techniques used in AI systems including : Neural networks Decision trees Present

More information

Analecta Vol. 8, No. 2 ISSN 2064-7964

Analecta Vol. 8, No. 2 ISSN 2064-7964 EXPERIMENTAL APPLICATIONS OF ARTIFICIAL NEURAL NETWORKS IN ENGINEERING PROCESSING SYSTEM S. Dadvandipour Institute of Information Engineering, University of Miskolc, Egyetemváros, 3515, Miskolc, Hungary,

More information

Vergleich der Versionen von Kapitel 7 des EU-GMP-Leitfadens (September 2012)

Vergleich der Versionen von Kapitel 7 des EU-GMP-Leitfadens (September 2012) (Valid until January 31, Principle Contract manufacture and analysis must be correctly defined, agreed and controlled in order to avoid misunderstandings which could result in a product or work of unsatisfactory

More information

Beurteilung von NewSmith Capital Partners

Beurteilung von NewSmith Capital Partners EFD Rohstoff 22. März 2005 Beurteilung von NewSmith Capital Partners Der durch den Bund und Kanton Zürich beigezogene Finanzberater NewSmith Capital Partners hat die vorgeschlagene Transaktion analysiert

More information

(Incorporated as a stock corporation in the Republic of Austria under registered number FN 33209 m)

(Incorporated as a stock corporation in the Republic of Austria under registered number FN 33209 m) Prospectus Supplement No. 2 Erste Group Bank AG (Incorporated as a stock corporation in the Republic of Austria under registered number FN 33209 m) EUR 30,000,000,000 Debt Issuance Programme This supplement

More information

Topological Data Analysis Applications to Computer Vision

Topological Data Analysis Applications to Computer Vision Topological Data Analysis Applications to Computer Vision Vitaliy Kurlin, http://kurlin.org Microsoft Research Cambridge and Durham University, UK Topological Data Analysis quantifies topological structures

More information

Dokumentation über die Übernahme von. "GS-R-3" (The Management System for Facilities and Activities) "Sicherheitskriterien für Kernkraftwerke"

Dokumentation über die Übernahme von. GS-R-3 (The Management System for Facilities and Activities) Sicherheitskriterien für Kernkraftwerke Dokumentation über die Übernahme von "GS-R-3" () in die "Sicherheitskriterien für Kernkraftwerke" REVISION D APRIL 2009 1. INTRODUCTION BACKGROUND 1.1 This Safety Requirements publication defines the requirements

More information

Vergleich der Versionen von Kapitel 1 des EU-GMP-Leitfaden (Oktober 2012) 01 July 2008 18 November 2009 31 Januar 2013 Kommentar Maas & Peither

Vergleich der Versionen von Kapitel 1 des EU-GMP-Leitfaden (Oktober 2012) 01 July 2008 18 November 2009 31 Januar 2013 Kommentar Maas & Peither Chapter 1 Quality Management Chapter 1 Quality Management System Chapter 1 Pharmaceutical Quality System Principle The holder of a Manufacturing Authorisation must manufacture medicinal products so as

More information

Data Mining with R. Decision Trees and Random Forests. Hugh Murrell

Data Mining with R. Decision Trees and Random Forests. Hugh Murrell Data Mining with R Decision Trees and Random Forests Hugh Murrell reference books These slides are based on a book by Graham Williams: Data Mining with Rattle and R, The Art of Excavating Data for Knowledge

More information

Part III: Machine Learning. CS 188: Artificial Intelligence. Machine Learning This Set of Slides. Parameter Estimation. Estimation: Smoothing

Part III: Machine Learning. CS 188: Artificial Intelligence. Machine Learning This Set of Slides. Parameter Estimation. Estimation: Smoothing CS 188: Artificial Intelligence Lecture 20: Dynamic Bayes Nets, Naïve Bayes Pieter Abbeel UC Berkeley Slides adapted from Dan Klein. Part III: Machine Learning Up until now: how to reason in a model and

More information

Applying Deep Learning to Car Data Logging (CDL) and Driver Assessor (DA) October 22-Oct-15

Applying Deep Learning to Car Data Logging (CDL) and Driver Assessor (DA) October 22-Oct-15 Applying Deep Learning to Car Data Logging (CDL) and Driver Assessor (DA) October 22-Oct-15 GENIVI is a registered trademark of the GENIVI Alliance in the USA and other countries Copyright GENIVI Alliance

More information

Exchange Synchronization AX 2012

Exchange Synchronization AX 2012 Exchange Synchronization AX 2012 Autor... Pascal Gubler Dokument... Exchange Synchronization 2012 (EN) Erstellungsdatum... 25. September 2012 Version... 2 / 17.06.2013 Content 1 PRODUKTBESCHREIBUNG...

More information

Classification and Prediction

Classification and Prediction Classification and Prediction Slides for Data Mining: Concepts and Techniques Chapter 7 Jiawei Han and Micheline Kamber Intelligent Database Systems Research Lab School of Computing Science Simon Fraser

More information

Specific Usage of Visual Data Analysis Techniques

Specific Usage of Visual Data Analysis Techniques Specific Usage of Visual Data Analysis Techniques Snezana Savoska 1 and Suzana Loskovska 2 1 Faculty of Administration and Management of Information systems, Partizanska bb, 7000, Bitola, Republic of Macedonia

More information

SPICE auf der Überholspur. Vergleich von ISO (TR) 15504 und Automotive SPICE

SPICE auf der Überholspur. Vergleich von ISO (TR) 15504 und Automotive SPICE SPICE auf der Überholspur Vergleich von ISO (TR) 15504 und Automotive SPICE Historie Software Process Improvement and Capability determination 1994 1995 ISO 15504 Draft SPICE wird als Projekt der ISO zur

More information

ARTIFICIAL INTELLIGENCE (CSCU9YE) LECTURE 6: MACHINE LEARNING 2: UNSUPERVISED LEARNING (CLUSTERING)

ARTIFICIAL INTELLIGENCE (CSCU9YE) LECTURE 6: MACHINE LEARNING 2: UNSUPERVISED LEARNING (CLUSTERING) ARTIFICIAL INTELLIGENCE (CSCU9YE) LECTURE 6: MACHINE LEARNING 2: UNSUPERVISED LEARNING (CLUSTERING) Gabriela Ochoa http://www.cs.stir.ac.uk/~goc/ OUTLINE Preliminaries Classification and Clustering Applications

More information

Cloud Performance Group 1. Cloud@Night Event. 14. Januar 2016 / Matthias Gessenay (matthias.gessenay@corporatesoftware.ch)

Cloud Performance Group 1. Cloud@Night Event. 14. Januar 2016 / Matthias Gessenay (matthias.gessenay@corporatesoftware.ch) 1 Cloud@Night Event 14. Januar 2016 / Matthias Gessenay (matthias.gessenay@corporatesoftware.ch) 2 Agenda SharePoint ABC Project Server ABC What s new in O365 4 SharePoint 2016 ABC A Access App-Support

More information

D A T A M I N I N G C L A S S I F I C A T I O N

D A T A M I N I N G C L A S S I F I C A T I O N D A T A M I N I N G C L A S S I F I C A T I O N FABRICIO VOZNIKA LEO NARDO VIA NA INTRODUCTION Nowadays there is huge amount of data being collected and stored in databases everywhere across the globe.

More information

Kapitel 2 Unternehmensarchitektur III

Kapitel 2 Unternehmensarchitektur III Kapitel 2 Unternehmensarchitektur III Software Architecture, Quality, and Testing FS 2015 Prof. Dr. Jana Köhler jana.koehler@hslu.ch IT Strategie Entwicklung "Foundation for Execution" "Because experts

More information

HYPO TIROL BANK AG. EUR 5,750,000,000 Debt Issuance Programme (the "Programme")

HYPO TIROL BANK AG. EUR 5,750,000,000 Debt Issuance Programme (the Programme) Third Supplement dated 29 December 2015 to the Prospectus dated 9 June 2015 This document constitutes a supplement (the "Third Supplement") within the meaning of Article 16 of the Directive 2003/71/EC

More information

Boosting. riedmiller@informatik.uni-freiburg.de

Boosting. riedmiller@informatik.uni-freiburg.de . Machine Learning Boosting Prof. Dr. Martin Riedmiller AG Maschinelles Lernen und Natürlichsprachliche Systeme Institut für Informatik Technische Fakultät Albert-Ludwigs-Universität Freiburg riedmiller@informatik.uni-freiburg.de

More information

Back Propagation Neural Networks User Manual

Back Propagation Neural Networks User Manual Back Propagation Neural Networks User Manual Author: Lukáš Civín Library: BP_network.dll Runnable class: NeuralNetStart Document: Back Propagation Neural Networks Page 1/28 Content: 1 INTRODUCTION TO BACK-PROPAGATION

More information

O D B C / R O C K E T ( B S 2 0 0 0 / O S D ) V 5. 0 F O R S E S A M / S Q L D A T E : F E B R U A R Y 2 0 0 8 *2 R E L E A S E N O T I C E

O D B C / R O C K E T ( B S 2 0 0 0 / O S D ) V 5. 0 F O R S E S A M / S Q L D A T E : F E B R U A R Y 2 0 0 8 *2 R E L E A S E N O T I C E O D B C / R O C K E T ( B S 2 0 0 0 / O S D ) V 5. 0 F O R S E S A M / S Q L D A T E : F E B R U A R Y 2 0 0 8 *2 R E L E A S E N O T I C E RELEASE NOTICE ODBC/ROCKET (BS2000/OSD) V 5.0 1 General.......................

More information

Pavlo Baron. Big Data and CDN

Pavlo Baron. Big Data and CDN Pavlo Baron Big Data and CDN Pavlo Baron www.pbit.org pb@pbit.org @pavlobaron What is Big Data Big Data describes datasets that grow so large that they become awkward to work with using on-hand database

More information

Multispectral stereo acquisition using 2 RGB cameras and color filters: color and disparity accuracy

Multispectral stereo acquisition using 2 RGB cameras and color filters: color and disparity accuracy Multispectral stereo acquisition using 2 RGB cameras and color filters: color and disparity accuracy (a) and Bernhard Hill (b) (a) Institute of Imaging and Computer Vision (b) Research Group Color and

More information

Applying Data Analysis to Big Data Benchmarks. Jazmine Olinger

Applying Data Analysis to Big Data Benchmarks. Jazmine Olinger Applying Data Analysis to Big Data Benchmarks Jazmine Olinger Abstract This paper describes finding accurate and fast ways to simulate Big Data benchmarks. Specifically, using the currently existing simulation

More information

Introduction to Machine Learning Using Python. Vikram Kamath

Introduction to Machine Learning Using Python. Vikram Kamath Introduction to Machine Learning Using Python Vikram Kamath Contents: 1. 2. 3. 4. 5. 6. 7. 8. 9. 10. Introduction/Definition Where and Why ML is used Types of Learning Supervised Learning Linear Regression

More information

Data Mining Techniques Chapter 6: Decision Trees

Data Mining Techniques Chapter 6: Decision Trees Data Mining Techniques Chapter 6: Decision Trees What is a classification decision tree?.......................................... 2 Visualizing decision trees...................................................

More information

Embedded Software Development and Test in 2011 using a mini- HIL approach

Embedded Software Development and Test in 2011 using a mini- HIL approach Primoz Alic, isystem, Slovenia Erol Simsek, isystem, Munich Embedded Software Development and Test in 2011 using a mini- HIL approach Kurzfassung Dieser Artikel beschreibt den grundsätzlichen Aufbau des

More information

Classifying Large Data Sets Using SVMs with Hierarchical Clusters. Presented by :Limou Wang

Classifying Large Data Sets Using SVMs with Hierarchical Clusters. Presented by :Limou Wang Classifying Large Data Sets Using SVMs with Hierarchical Clusters Presented by :Limou Wang Overview SVM Overview Motivation Hierarchical micro-clustering algorithm Clustering-Based SVM (CB-SVM) Experimental

More information

Data Mining Practical Machine Learning Tools and Techniques

Data Mining Practical Machine Learning Tools and Techniques Ensemble learning Data Mining Practical Machine Learning Tools and Techniques Slides for Chapter 8 of Data Mining by I. H. Witten, E. Frank and M. A. Hall Combining multiple models Bagging The basic idea

More information

Big Data Analytics CSCI 4030

Big Data Analytics CSCI 4030 High dim. data Graph data Infinite data Machine learning Apps Locality sensitive hashing PageRank, SimRank Filtering data streams SVM Recommen der systems Clustering Community Detection Web advertising

More information

1. Wenn der Spieler/die Spielerin noch keine IPIN hat, bitte auf den Button Register drücken

1. Wenn der Spieler/die Spielerin noch keine IPIN hat, bitte auf den Button Register drücken Welcome to IPIN The ipin (International Player Identification Number) is brought to you by the International Tennis Federation, the world governing body of tennis. All players who wish to compete in ITF

More information

The Changing Global Egg Industry

The Changing Global Egg Industry Vol. 46 (2), Oct. 2011, Page 3 The Changing Global Egg Industry - The new role of less developed and threshold countries in global egg production and trade 1 - Hans-Wilhelm Windhorst, Vechta, Germany Introduction

More information

Methods and Applications for Distance Based ANN Training

Methods and Applications for Distance Based ANN Training Methods and Applications for Distance Based ANN Training Christoph Lassner, Rainer Lienhart Multimedia Computing and Computer Vision Lab Augsburg University, Universitätsstr. 6a, 86159 Augsburg, Germany

More information

(51) Int Cl.: G06F 11/14 (2006.01) G06F 12/08 (2006.01)

(51) Int Cl.: G06F 11/14 (2006.01) G06F 12/08 (2006.01) (19) TEPZZ 488949B_T (11) EP 2 488 949 B1 (12) EUROPEAN PATENT SPECIFICATION (4) Date of publication and mention of the grant of the patent: 07.0.14 Bulletin 14/19 (21) Application number: 76367.4 (22)

More information

Steven C.H. Hoi School of Information Systems Singapore Management University Email: chhoi@smu.edu.sg

Steven C.H. Hoi School of Information Systems Singapore Management University Email: chhoi@smu.edu.sg Steven C.H. Hoi School of Information Systems Singapore Management University Email: chhoi@smu.edu.sg Introduction http://stevenhoi.org/ Finance Recommender Systems Cyber Security Machine Learning Visual

More information

Data mining techniques: decision trees

Data mining techniques: decision trees Data mining techniques: decision trees 1/39 Agenda Rule systems Building rule systems vs rule systems Quick reference 2/39 1 Agenda Rule systems Building rule systems vs rule systems Quick reference 3/39

More information

Smart Graphics: Methoden 3 Suche, Constraints

Smart Graphics: Methoden 3 Suche, Constraints Smart Graphics: Methoden 3 Suche, Constraints Vorlesung Smart Graphics LMU München Medieninformatik Butz/Boring Smart Graphics SS2007 Methoden: Suche 2 Folie 1 Themen heute Suchverfahren Hillclimbing Simulated

More information

Multipurpsoe Business Partner Certificates Guideline for the Business Partner

Multipurpsoe Business Partner Certificates Guideline for the Business Partner Multipurpsoe Business Partner Certificates Guideline for the Business Partner 15.05.2013 Guideline for the Business Partner, V1.3 Document Status Document details Siemens Topic Project name Document type

More information

Big Data: Big N. V.C. 14.387 Note. December 2, 2014

Big Data: Big N. V.C. 14.387 Note. December 2, 2014 Big Data: Big N V.C. 14.387 Note December 2, 2014 Examples of Very Big Data Congressional record text, in 100 GBs Nielsen s scanner data, 5TBs Medicare claims data are in 100 TBs Facebook 200,000 TBs See

More information

Introduction to Artificial Intelligence G51IAI. An Introduction to Data Mining

Introduction to Artificial Intelligence G51IAI. An Introduction to Data Mining Introduction to Artificial Intelligence G51IAI An Introduction to Data Mining Learning Objectives Introduce a range of data mining techniques used in AI systems including : Neural networks Decision trees

More information

www.infoplc.net Application example AC500 Scalable PLC for Individual Automation Communication between AC500 and KNX network abb

www.infoplc.net Application example AC500 Scalable PLC for Individual Automation Communication between AC500 and KNX network abb Application example www.infoplc.net AC500 Scalable PLC for Individual Automation Communication between AC500 and KNX network abb Content www.infoplc.net 1 Disclaimer...2 1.1 For customers domiciled outside

More information

So, how do you pronounce. Jilles Vreeken. Okay, now we can talk. So, what kind of data? binary. * multi-relational

So, how do you pronounce. Jilles Vreeken. Okay, now we can talk. So, what kind of data? binary. * multi-relational Simply Mining Data Jilles Vreeken So, how do you pronounce Exploratory Data Analysis Jilles Vreeken Jilles Yill less Vreeken Fray can 17 August 2015 Okay, now we can talk. 17 August 2015 The goal So, what

More information

Automatic Labeling of Lane Markings for Autonomous Vehicles

Automatic Labeling of Lane Markings for Autonomous Vehicles Automatic Labeling of Lane Markings for Autonomous Vehicles Jeffrey Kiske Stanford University 450 Serra Mall, Stanford, CA 94305 jkiske@stanford.edu 1. Introduction As autonomous vehicles become more popular,

More information

T O B C A T C A S E G E O V I S A T DETECTIE E N B L U R R I N G V A N P E R S O N E N IN P A N O R A MISCHE BEELDEN

T O B C A T C A S E G E O V I S A T DETECTIE E N B L U R R I N G V A N P E R S O N E N IN P A N O R A MISCHE BEELDEN T O B C A T C A S E G E O V I S A T DETECTIE E N B L U R R I N G V A N P E R S O N E N IN P A N O R A MISCHE BEELDEN Goal is to process 360 degree images and detect two object categories 1. Pedestrians,

More information

22. April 2010 Siemens Enterprise Communications

22. April 2010 Siemens Enterprise Communications Donnerstag, 26.04.2007 22. April 2010 Siemens Enterprise Communications GmbH & Co KG Copyright Siemens Copyright Enterprise Siemens Communications Enterprise Communications GmbH & KG 2007. 2010. All rights

More information

Data Mining Techniques

Data Mining Techniques 15.564 Information Technology I Business Intelligence Outline Operational vs. Decision Support Systems What is Data Mining? Overview of Data Mining Techniques Overview of Data Mining Process Data Warehouses

More information

LEARNING AGREEMENT FOR STUDIES

LEARNING AGREEMENT FOR STUDIES LEARNING AGREEMENT FOR STUDIES The Student Last name (s) First name (s) Date of birth Nationality 1 Sex [M/F] Academic year 20../20.. Study cycle 2 EQF level 6 (Bachelor) oder 7 (Master) Phone Subject

More information

Enterprise Architecture Management - Conclusion. Knut Hinkelmann

Enterprise Architecture Management - Conclusion. Knut Hinkelmann Enterprise Architecture Management - Conclusion Knut Hinkelmann Students Feedback Too much self-study including homework and assignment Less work at home Module has 6 ECTS à 30 hours Contact lessons are

More information

Lernsituation 9. Giving information on the phone. 62 Lernsituation 9 Giving information on the phone

Lernsituation 9. Giving information on the phone. 62 Lernsituation 9 Giving information on the phone Fachkunde 1, Lernfeld 2, Useful Office Vocabulary Lernsituation 9 Giving information on the phone Rolf astian, Managing Director of E Partners KG, recently visited the Promo World Fair in Düsseldorf, an

More information

Learning is a very general term denoting the way in which agents:

Learning is a very general term denoting the way in which agents: What is learning? Learning is a very general term denoting the way in which agents: Acquire and organize knowledge (by building, modifying and organizing internal representations of some external reality);

More information

Cross-validation for detecting and preventing overfitting

Cross-validation for detecting and preventing overfitting Cross-validation for detecting and preventing overfitting Note to other teachers and users of these slides. Andrew would be delighted if ou found this source material useful in giving our own lectures.

More information

An Incrementally Trainable Statistical Approach to Information Extraction Based on Token Classification and Rich Context Models

An Incrementally Trainable Statistical Approach to Information Extraction Based on Token Classification and Rich Context Models Dissertation (Ph.D. Thesis) An Incrementally Trainable Statistical Approach to Information Extraction Based on Token Classification and Rich Context Models Christian Siefkes Disputationen: 16th February

More information

An analytical redundancy approach towards decentralized autonomous fault detection in wireless structural health monitoring

An analytical redundancy approach towards decentralized autonomous fault detection in wireless structural health monitoring 1 An analytical redundancy approach towards decentralized autonomous fault detection in wireless structural health monitoring Katrin Jahr, Kosmas Dragos and Eike Tauscher Chair of Computing in Civil Engineering

More information

Symantec Backup Exec (TM) 13 Installation Log

Symantec Backup Exec (TM) 13 Installation Log v Symantec Backup Exec (TM) 13 Installation Log 05-26-2010,15:07:12 : Explorer exists. Launching UI. 05-26-2010,15:07:14 : Executing managed _Setup: 05-26-2010,15:07:14 : C:\Dokumente und orms_multilingual_dvd\be\winnt\install\be32\install\_setup.exe

More information

IBM Security. Alle Risiken im Blick und bessere Compliance Kumulierte und intelligente Security Alerts mit QRadar Security Intelligence

IBM Security. Alle Risiken im Blick und bessere Compliance Kumulierte und intelligente Security Alerts mit QRadar Security Intelligence IBM Security Alle Risiken im Blick und bessere Compliance Kumulierte und intelligente Security Alerts mit QRadar Security Intelligence Peter Kurfürst Vertrieb IBM Security Lösungen Enterprise-Kunden Baden-Württemberg

More information

NEURAL NETWORKS IN DATA MINING

NEURAL NETWORKS IN DATA MINING NEURAL NETWORKS IN DATA MINING 1 DR. YASHPAL SINGH, 2 ALOK SINGH CHAUHAN 1 Reader, Bundelkhand Institute of Engineering & Technology, Jhansi, India 2 Lecturer, United Institute of Management, Allahabad,

More information

Decision Trees from large Databases: SLIQ

Decision Trees from large Databases: SLIQ Decision Trees from large Databases: SLIQ C4.5 often iterates over the training set How often? If the training set does not fit into main memory, swapping makes C4.5 unpractical! SLIQ: Sort the values

More information

Color Histogram Normalization using Matlab and Applications in CBIR. László Csink, Szabolcs Sergyán Budapest Tech SSIP 05, Szeged

Color Histogram Normalization using Matlab and Applications in CBIR. László Csink, Szabolcs Sergyán Budapest Tech SSIP 05, Szeged Color Histogram Normalization using Matlab and Applications in CBIR László Csink, Szabolcs Sergyán Budapest Tech SSIP 05, Szeged Outline Introduction Demonstration of the algorithm Mathematical background

More information

Previous Lectures. B-Trees. External storage. Two types of memory. B-trees. Main principles

Previous Lectures. B-Trees. External storage. Two types of memory. B-trees. Main principles B-Trees Algorithms and data structures for external memory as opposed to the main memory B-Trees Previous Lectures Height balanced binary search trees: AVL trees, red-black trees. Multiway search trees:

More information

SPECIAL PERTURBATIONS UNCORRELATED TRACK PROCESSING

SPECIAL PERTURBATIONS UNCORRELATED TRACK PROCESSING AAS 07-228 SPECIAL PERTURBATIONS UNCORRELATED TRACK PROCESSING INTRODUCTION James G. Miller * Two historical uncorrelated track (UCT) processing approaches have been employed using general perturbations

More information

Summary Data Mining & Process Mining (1BM46) Content. Made by S.P.T. Ariesen

Summary Data Mining & Process Mining (1BM46) Content. Made by S.P.T. Ariesen Summary Data Mining & Process Mining (1BM46) Made by S.P.T. Ariesen Content Data Mining part... 2 Lecture 1... 2 Lecture 2:... 4 Lecture 3... 7 Lecture 4... 9 Process mining part... 13 Lecture 5... 13

More information

AnyWeb AG 2008 www.anyweb.ch

AnyWeb AG 2008 www.anyweb.ch HP SiteScope (End-to-End Monitoring, System Availability) Christof Madöry AnyWeb AG ITSM Practice Circle September 2008 Agenda Management Technology Agentless monitoring SiteScope in HP BTO SiteScope look

More information

Classification Techniques (1)

Classification Techniques (1) 10 10 Overview Classification Techniques (1) Today Classification Problem Classification based on Regression Distance-based Classification (KNN) Net Lecture Decision Trees Classification using Rules Quality

More information

How does the Kinect work? John MacCormick

How does the Kinect work? John MacCormick How does the Kinect work? John MacCormick Xbox demo Laptop demo The Kinect uses structured light and machine learning Inferring body position is a two-stage process: first compute a depth map (using structured

More information

Timebox Planning View der agile Ansatz für die visuelle Planung von System Engineering Projekt Portfolios

Timebox Planning View der agile Ansatz für die visuelle Planung von System Engineering Projekt Portfolios Agile Leadership Day 2015 Markus Giacomuzzi - Siemens Building Technologies Headquarters Zug Timebox Planning View der agile Ansatz für die visuelle Planung von System Engineering Projekt Portfolios structure

More information

Mobile Hybrid Assistance Systems for Education and Training with Smartpads

Mobile Hybrid Assistance Systems for Education and Training with Smartpads Mobile Hybrid Assistance Systems for Education and Training with Smartpads Ute von Jan, Christoph Noll, Marianne Behrends, Urs-Vito Albrecht Hannover Medical School Peter L. Reichertz Institute for Medical

More information

RAT DER EUROPÄISCHEN UNION. Brüssel, den 2. März 2012 (06.03) (OR. en) 6051/12 INF 11 API 11 JUR 50. I/A-PUNKT-VERMERK Gruppe "Information"

RAT DER EUROPÄISCHEN UNION. Brüssel, den 2. März 2012 (06.03) (OR. en) 6051/12 INF 11 API 11 JUR 50. I/A-PUNKT-VERMERK Gruppe Information RAT DER EUROPÄISCHEN UNION Brüssel, den 2. März 2012 (06.03) (OR. en) 6051/12 INF 11 API 11 JUR 50 I/A-PUNKT-VERMERK der Gruppe "Information" für den AStV (2. Teil)/Rat Nr. Vordokument: 6050/12 Betr.:

More information

Thermodynamic efficiency of an actuator that provides the mechanical movement for the driven equipments:

Thermodynamic efficiency of an actuator that provides the mechanical movement for the driven equipments: 1. Introduction 1.1. Industry Automation Industry automation is the term that describes a vital development programme of a production community where the project engineers build up automated manufacturing

More information

Lecture 10: Regression Trees

Lecture 10: Regression Trees Lecture 10: Regression Trees 36-350: Data Mining October 11, 2006 Reading: Textbook, sections 5.2 and 10.5. The next three lectures are going to be about a particular kind of nonlinear predictive model,

More information