[PDF] [PDF] Data Mining I Summer semester 2019 Lecture 1: Introduction

[PDF] Deep Learning is eating software

Pré-requis • Python (laboratoire, TP) • Certaine connaissance du machine learning • Probabilité • Algèbre linéaire • Dérivée • Un peu d'optimisation 6 

[PDF] Deep Learning is alchemy

17 jan 2020 · Pré-requis • Python (laboratoire, TP) • Certaine connaissance de l' apprentissage machine • Probabilité • Algèbre linéaire • Dérivée • Un peu 

[PDF] Présentation PowerPoint

Nécessite Python (inclus dans le “package” d'installation) • Ajout et Educational: widgets pour l'enseignement des méthodes de machine learning (k- means,

[PDF] formation au langage python - IA Academie

Comprenant : La formation, les supports de cours et les outils associés Prérequis : Être à l'aise avec les sujets traitant de l'informatique, tel le Machine Learning

[PDF] Deep Learning with Python

This book is written for people with Python programming experience who want to get started with machine learning and deep learning But this book can also be 

[PDF] Présentation PowerPoint - French Tech Brest +

A variant of machine learning engineer is called Python / R / (C++) Deep learning is part of a broader family of machine learning methods based on artificial 

[PDF] Deep Learning Seance 1pdf - Indico de lIN2P3

Réseaux de neurones et deep learning À partir de mi-octobre Séances de 30/ 40 mn suivies de 20 mn de discussion Utilisations courantes du deep learning Quiz pour s'entraîner et exercices de programmation (Python) : fortement

[PDF] Using Machine Learning & Deep Learning With ArcGIS - gisworx

Tensor Flow: end-to-end open source platform for machine learning Keras: Open -source neural-network library written in Python Capable of running on top of 

[PDF] Data Mining I Summer semester 2019 Lecture 1: Introduction

15 mai 2019 · Why to study Data Mining/Machine Learning – famous quotes* □ Source: https://www slideshare net/IBMBDA/myths- Goal: Running a data analysis process in python, from data selection to pattern evaluation ▫

[PDF] Machine Learning avec Python - Institut Quantmetry

Le Machine Learning (apprentissage automatique) constitue aujourd'hui l'une des techniques les plus efficace pour extraire la connaissance et la valeur de la 

[PDF] macintosh

[PDF] macleay valley travel reviews

[PDF] macleay valley travel tasmania

[PDF] macos 10.15 compatibility

[PDF] macos catalina security features

[PDF] macos security guide

[PDF] macos server

[PDF] macos server mojave

[PDF] macos virtualization license

[PDF] macromolecules

[PDF] macron ce soir

[PDF] macros in 8086 microprocessor pdf

[PDF] macros in excel pdf books

[PDF] macy's billing

[PDF] macy's card discount exclusions

Data Mining I

Summer semester 2019

Lecture 1: Introduction

Lectures: Prof. Dr. Eirini Ntoutsi

TAs: Tai Le Quy, VasileiosIosifidis, Maximilian Idahl, ShaheerAsghar, WazedAli

Institut für Verteilte Systeme

AG Intelligente Systeme -Data Mining group

About me

"03/2016 -presentAssociate Professor Faculty of Electrical Engineering & Computer Science Leibniz University Hannover

L3S Research Center(since May 2016)

"02/2012 -02/2016Post-doctoral researcher & lecturer

Institute for Informatics,LMU Munich, Germany

"02/2010 -01/2012 Alexander von Humboldt postdoc fellow

Institute for Informatics, LMU Munich, Germany

"2009: Data Mining Expert National Hellenic Organization (OTE), Athens, Greece "04/2007 -02/2009Co-Founder and AI expert

NeeMoStartup, Greece

"09/2003 -09/2008 PhD in Data Mining

University of Piraeus, Athens, Greece

"09/2001 -09/2003MSc, Computer Science/ Text Mining

Polytechnic School, University of Patras, Greece

"09/1996 -09/2001 Diploma, Computer Engineering and Informatics/ AI Games

Polytechnic School, University of Patras, Greece

2Learning from streaming data

Current focus areas:

Data Stream Mining/ Adaptive Machine Learning

Responsible AI: Fairness-Aware Machine Learning

Outline

3Data Mining I @SS19: Introduction

Why to study Data Mining/Machine Learning -famous quotes*

Microsoft)

Yahoo)

Microsoft)

4 *Source: Pedro Domingos http://courses.cs.washington.edu/courses/cse446/15sp/slides/intro.pdf

Data Mining I @SS19: Introduction

Disclaimer:I use theterms data miningandmachine learning (sometimes also Artificial Intelligence (AI) interchangeably here and through the lecture. We will discuss the similarities/differences later. In both cases, we talk to learning from data. Data Mining -Data Science -Big Data -Machine Learning -Deep Learning 5 ͞Big data is like teenage sedž͗ eǀeryone talks about it, nobody really knows how to do it, everyone thinks everyone else is doing it, so everyone claims they are doing it.͞

Source: Dan Ariely, Duke University

Data Mining I @SS19: Introduction

6

Source: Google trends, query on 9.4.2019

Data Mining I @SS19: Introduction

Why to study Data Mining -Data Scientist: The sexiest job of 21stcentury 7

Source: Harvard Business Review. Data Scientist: The Sexiest Job of the 21st Century. October 2012 link

Data Mining I @SS19: Introduction

Source: https://www.slideshare.net/IBMBDA/myths-

A good conjuncture for ML/DM/DS (data-driven learning)

8Data Mining I @SS19: Introduction

Data deluge

Machine Learning

advances

Computer power

Enthusiasm

World-wide competition on Artificial Intelligence (AI)

Generation, 19/3/2019, Berlin

There are 3 fierce competitions

9Data Mining I @SS19: Introduction

Outline

11Data Mining I @SS19: Introduction

Why we need Data Mining

Telecommunication

Astronomy

BanksBiology

Internet

Supermarkets

12 IoT

Data Mining I @SS19: Introduction

Examples of data sources: The Internet

13

Web 2.0: A world of opinions

User generated content

Data Mining I @SS19: Introduction

Source: http://www.internetlivestats.com/internet-users/

Examples of data sources: Internet of things

software, sensors, and network connectivity, which enables these objects to collect and exchange data. Source: https://en.wikipedia.org/wiki/Internet_of_Things 14

Image source:http://tinyurl.com/prtfqxf

Source: http://blogs.cisco.com/diversity/the-internet-of-things-infographic During 2008, the number of things connected to the These things are everything, smartphones, tablets,

Data Mining I @SS19: Introduction

Examples of data sources: data intensive science

15 Slide from:http://research.microsoft.com/en-us/um/people/gray/talks/nrc-cstb_escience.ppt bepoweredbyadvancedcomputing capabilitiesthathelpresearchers manipulateandexploremassivedatasets." -The Fourth Paradigm -Microsoft

Examples of e-science applications:

Earth and environment

Health and wellbeing

E.g., The HumanGenome Project(HGP)

Citizen science

Scholarly communication

Basic science

E.g., CERN

Data Mining I @SS19: Introduction

Examples of data sources: Manufacturing

Source: https://www.technologyreview.com/s/609770/andrew-ng-says-factories-are-ais-next-frontier/ 16

Image source: https://images.readwrite.com/wp-

Companies are making major investments in AI and

industrial analytics to help drive their digital transformation

Data Mining I @SS19: Introduction

Image source: https://cdn-sv1.deepsense.ai/wp-

manufacturing-1140x337.jpg lecture ї priǀacy aware data mining (https://eugdpr.org/)

17Data Mining I @SS19: Introduction

From data to knowledge of different types

18Data Mining I @SS19: Introduction

DataMethodsKnowledge

Call records

Movie ratings

Telescope

images

Outlier DetectionDetect fraud cases

Collaborative filteringRecommend movies to users

ClassificationIs it an "early», "intermediate» or "late formation» star? News articlesClusteringWhat are the topics people discuss about in the news today?

Short break (5') -Get to know us better

19Data Mining I @SS19: Introduction

Outline

20Data Mining I @SS19: Introduction

What is KDD

Knowledge Discovery in Databases(KDD)is the nontrivial processof identifying valid, novel, potentially

useful, and ultimatelyunderstandablepatternsin data. [Fayyad, Piatetsky-Shapiro, and Smyth 1996]

Remarks:

some post-processing

21Data Mining I @SS19: Introduction

Clarification:The term databases does not refer exclusively to relational databases storing structured

The KDD process and the Data Mining step

22

Patterns

Knowledge

[Fayyad, Piatetsky-Shapiro & Smyth, 1996]

Transformed data

Target data

Preprocessed data

Selection:ͻSelect a relevant dataset or focus on a subset of a datasetͻFile / DB/Preprocessing/Cleaning:ͻIntegration of data from different data sourcesNoise removalMissing valuesTransformation:ͻSelect useful featuresͻFeature transformation/ discretizationͻDimensionality reductionData Mining:ͻSearch for patterns of interest Evaluation:ͻEvaluate patterns based on interestingness measuresͻStatistical validation of the ModelsͻVisualizationͻDescriptive Statistics

Data

Data Mining I @SS19: Introduction

A modern version: The Data Science process

23Data Mining I @SS19: Introduction

The interdisciplinary nature of KDD 1/2

24
KDD

Machine

Learning

Databases

Statistics

Data visualization

Pattern

recognition

AlgorithmsOther

disciplines

Data Mining I @SS19: Introduction

The interdisciplinary nature of KDD 2/2

25

StatisticsMachine Learning

Databases

KDD

Model based inference

Focus on numerical

data

Theory + methods

Focus on small datasets

Scalability to large data sets

New data types (web data, micro-arrays, social data ...)

Integration with commercial databases

[Chen, Han & Yu 1996] [Berthold & Hand 1999][Mitchell 1997]

Data Mining I @SS19: Introduction

How do machines learn?

1959)

26Data Mining I @SS19: Introduction

Algorithms

Models

Models

(semi)Automatic decision making Data How can we build computer programs that automatically improve with experience?

Tom Mitchell, Machine Learning book

More formally: How do machines learn?

performance measure P, if its performance at tasks in T, as measured by P, improves with experience E.

Tom Mitchell, Machine Learning 1997.

27Data Mining I @SS19: Introduction

(Machine) Learning from experience/feedback 1/2 problemͬ application" columns are the features.

28Data Mining I @SS19: Introduction

(Machine) Learning from experience/feedback 2/2

͞teacher"ͬ"edžpert͞

dataset

29Data Mining I @SS19: Introduction

Unlabeleddataset

Labeleddataset

Lecture 2 is devoted on getting to

know our data!!! Short break (5') -Modeling students data for the exam performance task

30Data Mining I @SS19: Introduction

Outline

31Data Mining I @SS19: Introduction

Different learning tasks

Based on the feedback we have on the data, we can distinguish between: the teacher

32Data Mining I @SS19: Introduction

Supervised learning

Reinforcement learning

Unsupervised learning

Different learning tasks: Supervised learning

unseen instance to predict its class label

33Data Mining I @SS19: Introduction

Classification: an example

34Data Mining I @SS19: Introduction

Screw Nails

Paper clips

Height [cm]

Width[cm]

instancewidthheightclass

12,64,5Screw

23,77,3Nails

34,16,5PaperClips

48,58,1Screw

59,55,5Nails

New object New object

Classification applications 1/2

35Data Mining I @SS19: Introduction

Classification applications 2/2

status, etc.

36Data Mining I @SS19: Introduction

Example: Google News

37Data Mining I @SS19: Introduction

A huge variety of classification algorithms

38Data Mining I @SS19: Introduction

quotesdbs_dbs19.pdfusesText_25