SlideShare ist ein Scribd-Unternehmen logo
1 von 32
Zürcher Fachhochschule
Deep Learning @ ZHAW
Thilo Stadelmann, Mark Cieliebak & Yves Pauchard
InIT Colloquium, 15. April 2015, Winterthur
Zürcher Fachhochschule
2
Agenda
Overview
• What is Deep Learning? ‘15
• Our stake in it
InIT Use Case: Text Analytics ‘10
•
InIT Use Case: Face Recognition ‘10
•
Zürcher Fachhochschule
3
Deep Learning is…
…a hot topic!
Zürcher Fachhochschule
4
Deep Learning is…
…Continued Neural Network Research
What’s new?
• Novel architectures (wider, deeper)
• Faster and better training
(e.g., understanding of Backpropagation’s “vanishing gradient” problem, good initial weights)
• Better regularization (e.g., Dropout, Max-pooling etc.)
• Big Data (or augmentation) and corresponding computational power on GPUs
 «Add as many parameters as possible for your hardware and train the hell out of
it with proper regularization» (Yann LeCun)
Zürcher Fachhochschule
5
Deep Learning is…
… Successful
Areas of successful application:
• Computer Vision (detection, segmentation, recognition, OCR, video analysis)
• Speech Processing (Recognition, Siri etc.)
• Natural Language Processing (Translation, Sentiment Analysis)
• Metric Learning (distances, invariances, hashing)
• Prediction & Forecasting (financial, time series)
Red titled slides by Jonathan Masci
Zürcher Fachhochschule
6
Technical Idea
Learning Features, not just rules
Hand-engineering features is tedious
 Let each layer learn a new representation of the data by itself
Actual learning is…
• governed by the learning target (input-output pairs & objective function),
• facilitated by constraints & regularizations (e.g., sparsity to learn distributed codes),
• enforced by the Backpropagation algorithm (1970-1989)
What is learned?
• Highly non-linear functions purely from data
• Hierarchies of features, combinations of elements (distributed codes)
State of the Art
• CNNs (Convolutional Neural Networks) for vision tasks and beyond
 Relatively easy to use, very successful, biologically inspired, broad user basis
• RNNs (Recurrent Neural networks) for sequences and hard tasks
 Turing complete, hot research topic Honglak Lee, University of Michigan
Yan et al., National University of Singapore
Zürcher Fachhochschule
7
The Deep Learning Market
… and what we do about it!
Strategic relevance
• 3 years ago: <10 research groups at «ivy league» universities
• 01/2014: Google acquires DeepMind for 500 Mio. $ (startup by IDSIA / Ticino)
• Currently:
• Courses / books / software frameworks are all «beta versions»
• Boundaries between research and application are strongly domain-specific
• Outlook: Could be a tool like «SVM» in 2-5 years
Deep Learning @ Datalab
• Hardware invests: 2 multi-GPU Workstations
http://www.zhaw.ch/de/zhaw/institute-zentren/uebergreifende-institute-zentren/dlab/hardware.html
• People invests: 13 researchers formed the Deep Learning Journals Club in 2014
deeplearning@downbirn.zhaw.ch
• Projects:
• 2 internal projects finished (see use cases later!)
• 2 CTI projects just got funded (start this summer)
• Several proposals pending
Zürcher Fachhochschule
8
Use Case «Text Analytics»
Mark Cieliebak

Zürcher Fachhochschule
9
Goal: Turn text
into information
Sentiment Analysis
Q&A
Named Entity Extraction
Text Summarization
Machine Translation
Spelling Correction
Information Retrieval
What is "Text Analytics"?
Zürcher Fachhochschule
10
Rule-Based Corpus-Based
Deep Learning
Predicted
Label
Approaches to Text Analytics
Zürcher Fachhochschule
11
Predicted
Label
Feature-Based Text Analytics
Zürcher Fachhochschule
12
Sample Features for Tweets
Word ngrams: presence or absence of contiguous sequences of 1, 2, 3, and 4
tokens; noncontiguous ngrams
POS: the number of occurrences of each part-of-speech tag
Sentiment Lexica: each word annotated with tonality score (-1..0..+1)
Negation: the number of negated contexts
Punctuation: the number of contiguous sequences of exclamation marks, question
marks, and both exclamation and question marks
Emoticons: presence or absence, last token is a positive or negative emoticon;
Hashtags: the number of hashtags;
Elongated words: the number of words with one character repeated (e.g. ‘soooo’)
from: Mohammad et al., SemEval 2013
Zürcher Fachhochschule
13
Feature-Based Text Analytics
Most Important Issues
• Requires large annotated corpora
• Depends on good features
[6]
Zürcher Fachhochschule
14
Deep Learning on Text
Deep Learning:
It's all about Word Vectors!
Zürcher Fachhochschule
15
Word2Vec
• Huge set of text samples (billions of
words)
• Extract dictionary
• Word-Matrix: k-dimensional vector for
each word (k typically 50-500)
• Word vector initialized randomly
• Train word vectors to predict next
words, given a sequence of words
from sample text
Major contributions by Bengio et al. 2003, Collobert&Weston 2008, Socher et al. 2011, Mikolov et al. 2013
Zürcher Fachhochschule
16
The Magic of Word Vectors
King - Man + Woman ≈ Queen
Live Demo on 100b words from Google News dataset: http://radimrehurek.com/2014/02/word2vec-tutorial/
Zürcher Fachhochschule
17
Relations Learned by Word2Vec
[11]
Zürcher Fachhochschule
18
Using Word Vectors in NLP
Collobert et al., 2011:
• SENNA: Generic NLP System based on word vectors
• Solves many NLP-Tasks as good as benchmark systems
Zürcher Fachhochschule
19
Sentiment Analysis
"… WiFi Analytics is a free Android app that I find
very handy when it comes to troubleshooting and
monitoring a home network. "
Zürcher Fachhochschule
20
Deep Learning and Sentiment
• Maas et al., 2011: word vectors with sentiment context
• Socher et al, 2013: Representing sentence structures
as trees with sentiment annotation
• Quoc and Mikolov, 2014:
"Paragraph Vectors"
wonderful terrible
amazing awful
Zürcher Fachhochschule
21
Words and Images
Untrained
Class
Demo: http://www.clarifai.com/#demo
Zürcher Fachhochschule
22
Use Case «Face Recognition»
Yves Pauchard

Zürcher Fachhochschule
23
piVision: Face recognition on a Raspberry Pi
Zürcher Fachhochschule
24
What is face recognition?
Detection: Is this a face or not?
Verification: Are these two pictures showing the same face?
Identification: Is this Yves?
Zürcher Fachhochschule
25
Pipeline
Detect Align
Feature
extractor
Train
Pre-processor Model
Filter
Recognizer
Predict
Extract face Correct
pose
Correct
illumination
Dimensionality
reduction
Classification
Zürcher Fachhochschule
26
Software development
• Python (OpenCV) + PyCharm + SVN + TeamCity
(Raspberry Pi and Linux agents)
• Timing and accuracy test after each commit
Zürcher Fachhochschule
27
Baseline: Fisherfaces (OpenCV)
Detect Align
Feature
extractor
Train
Pre-processor Model
Filter
Recognizer
Predict
Viola & Jones 2D similarity
transform
Gamma +
DoG
Principal
Component
Analysis
Linear Discriminate
Analysis
Zürcher Fachhochschule
28
Deep Learning
Detect Align
Feature
extractor
Train
Pre-processor Model
Filter
Recognizer
Predict
Viola & Jones Local binary
pattern +
ellipse
Convolutional Neural Network:
Features are learned
Zürcher Fachhochschule
29
Experiment
Testing outdoors (used exclusively for testing)
Training indoors (used for learning)
Approx. 40 images of 6 individuals acquired in 2 batches.
For CNN training, an augmented set was used, i.e.
additional training images were synthetically created.
Zürcher Fachhochschule
30
Results
Zürcher Fachhochschule
31
Interesting findings
• Alignment is crucial for baseline algorithm – time consuming
• CNN needs to be trained on desktop PC with GPU
• Training data augmentation for CNN can effectively replace
the alignment step – saving time
• CNN outperforms baseline algorithm 99.6 % : 96.9 %,
dropping less images and saving time.
• Let’s see it running:
https://www.youtube.com/watch?v=oI1eJa-UWNU
Zürcher Fachhochschule
32
Further Reading
• Very brief history with some links (2015)
http://dublin.zhaw.ch/~stdm/?p=241
• Comprehensive history & survey (2015)
Schmidhuber, “Deep Learning in Neural Networks: An Overview”
http://arxiv.org/abs/1404.7828
• Deep Learning Kick-off (2006  of historical interest)
Hinton et al., “A Fast Learning Algorithm for Deep Belief Nets”
http://www.cs.toronto.edu/~hinton/absps/ncfast.pdf
• Very practical overview of Convolutional Neural Networks (CNNs, 1998)
LeCun et al., “Gradient-Based Learning Applied to Document Recognition”
http://yann.lecun.com/exdb/publis/pdf/lecun-98.pdf
• Cool application for which Google paid 500 Mio. $ (2015)
Mnih et al, “Human-Level Control through Deep Reinforcement Learning”
http://www.nature.com/nature/journal/v518/n7540/full/nature14236.html

Weitere ähnliche Inhalte

Was ist angesagt?

II-SDV 2017: The Next Era: Deep Learning for Biomedical Research
II-SDV 2017: The Next Era: Deep Learning for Biomedical ResearchII-SDV 2017: The Next Era: Deep Learning for Biomedical Research
II-SDV 2017: The Next Era: Deep Learning for Biomedical Research
Dr. Haxel Consult
 
Moving Your Machine Learning Models to Production with TensorFlow Extended
Moving Your Machine Learning Models to Production with TensorFlow ExtendedMoving Your Machine Learning Models to Production with TensorFlow Extended
Moving Your Machine Learning Models to Production with TensorFlow Extended
Jonathan Mugan
 

Was ist angesagt? (16)

From Raw Data to Deployed Product. Fast & Agile with CRISP-DM
From Raw Data to Deployed Product. Fast & Agile with CRISP-DMFrom Raw Data to Deployed Product. Fast & Agile with CRISP-DM
From Raw Data to Deployed Product. Fast & Agile with CRISP-DM
 
II-SDV 2017: The Next Era: Deep Learning for Biomedical Research
II-SDV 2017: The Next Era: Deep Learning for Biomedical ResearchII-SDV 2017: The Next Era: Deep Learning for Biomedical Research
II-SDV 2017: The Next Era: Deep Learning for Biomedical Research
 
Himansu sahoo resume-ds
Himansu sahoo resume-dsHimansu sahoo resume-ds
Himansu sahoo resume-ds
 
雲端影音與物聯網平台的軟體工程挑戰:以 Skywatch 為例-陳維超
雲端影音與物聯網平台的軟體工程挑戰:以 Skywatch 為例-陳維超雲端影音與物聯網平台的軟體工程挑戰:以 Skywatch 為例-陳維超
雲端影音與物聯網平台的軟體工程挑戰:以 Skywatch 為例-陳維超
 
巨量與開放資料之創新機會與關鍵挑戰-曾新穆
巨量與開放資料之創新機會與關鍵挑戰-曾新穆巨量與開放資料之創新機會與關鍵挑戰-曾新穆
巨量與開放資料之創新機會與關鍵挑戰-曾新穆
 
Machine Learning Goes Production
Machine Learning Goes ProductionMachine Learning Goes Production
Machine Learning Goes Production
 
Moving Your Machine Learning Models to Production with TensorFlow Extended
Moving Your Machine Learning Models to Production with TensorFlow ExtendedMoving Your Machine Learning Models to Production with TensorFlow Extended
Moving Your Machine Learning Models to Production with TensorFlow Extended
 
Introduction to Data Science
Introduction to Data ScienceIntroduction to Data Science
Introduction to Data Science
 
Demystifying Machine Learning and Artificial Intelligence
Demystifying Machine Learning and Artificial IntelligenceDemystifying Machine Learning and Artificial Intelligence
Demystifying Machine Learning and Artificial Intelligence
 
[系列活動] 機器學習速遊
[系列活動] 機器學習速遊[系列活動] 機器學習速遊
[系列活動] 機器學習速遊
 
Polong Lin(林伯龍)/how to approach data science problems from start to end
Polong Lin(林伯龍)/how to approach data science problems from start to endPolong Lin(林伯龍)/how to approach data science problems from start to end
Polong Lin(林伯龍)/how to approach data science problems from start to end
 
Machine learning 101 dkom 2017
Machine learning 101 dkom 2017Machine learning 101 dkom 2017
Machine learning 101 dkom 2017
 
Multimodal Learning Analytics
Multimodal Learning AnalyticsMultimodal Learning Analytics
Multimodal Learning Analytics
 
Visual concept learning
Visual concept learningVisual concept learning
Visual concept learning
 
CRISP-DM - Agile Approach To Data Mining Projects
CRISP-DM - Agile Approach To Data Mining ProjectsCRISP-DM - Agile Approach To Data Mining Projects
CRISP-DM - Agile Approach To Data Mining Projects
 
Machine learning 101 sit hvr
Machine learning 101 sit hvrMachine learning 101 sit hvr
Machine learning 101 sit hvr
 

Andere mochten auch

Object recognition
Object recognitionObject recognition
Object recognition
akkichester
 
Breeam lezing knv koeltechniek jan2014
Breeam lezing knv koeltechniek jan2014Breeam lezing knv koeltechniek jan2014
Breeam lezing knv koeltechniek jan2014
Olaf Buter
 

Andere mochten auch (20)

Wie die Swiss Alliance for Data-Intensive Services datenbasierte Mehrwerte sc...
Wie die Swiss Alliance for Data-Intensive Services datenbasierte Mehrwerte sc...Wie die Swiss Alliance for Data-Intensive Services datenbasierte Mehrwerte sc...
Wie die Swiss Alliance for Data-Intensive Services datenbasierte Mehrwerte sc...
 
Data Science - (K)eine Teenagerliebe
Data Science - (K)eine TeenagerliebeData Science - (K)eine Teenagerliebe
Data Science - (K)eine Teenagerliebe
 
Der Wert von Daten in Zeiten von "Big Data"
Der Wert von Daten in Zeiten von "Big Data"Der Wert von Daten in Zeiten von "Big Data"
Der Wert von Daten in Zeiten von "Big Data"
 
Was denken denkende Maschinen?
Was denken denkende Maschinen?Was denken denkende Maschinen?
Was denken denkende Maschinen?
 
Object recognition
Object recognitionObject recognition
Object recognition
 
Computer Vision, Deep Learning, OpenCV
Computer Vision, Deep Learning, OpenCVComputer Vision, Deep Learning, OpenCV
Computer Vision, Deep Learning, OpenCV
 
Foliensatz der RWTH 2014
Foliensatz der RWTH 2014Foliensatz der RWTH 2014
Foliensatz der RWTH 2014
 
The Psychology Behind Pair Designing
The Psychology Behind Pair DesigningThe Psychology Behind Pair Designing
The Psychology Behind Pair Designing
 
Breeam lezing knv koeltechniek jan2014
Breeam lezing knv koeltechniek jan2014Breeam lezing knv koeltechniek jan2014
Breeam lezing knv koeltechniek jan2014
 
SAP Inside Track Wroclow - Bluetooth the World
SAP Inside Track Wroclow - Bluetooth the WorldSAP Inside Track Wroclow - Bluetooth the World
SAP Inside Track Wroclow - Bluetooth the World
 
dda-12-2009
dda-12-2009dda-12-2009
dda-12-2009
 
Due diligence for early stage investing
Due diligence for early stage investingDue diligence for early stage investing
Due diligence for early stage investing
 
Matter March 2015
Matter March 2015Matter March 2015
Matter March 2015
 
Venture-Capital-Broschüre. Wenn Ideen groß werden
Venture-Capital-Broschüre. Wenn Ideen groß werdenVenture-Capital-Broschüre. Wenn Ideen groß werden
Venture-Capital-Broschüre. Wenn Ideen groß werden
 
AWS Black Belt Techシリーズ AWS OpsWorks
AWS Black Belt Techシリーズ  AWS OpsWorksAWS Black Belt Techシリーズ  AWS OpsWorks
AWS Black Belt Techシリーズ AWS OpsWorks
 
Online Karrieretag Hamburg 2013 - eBay, Inc overview for young professionals
Online Karrieretag Hamburg 2013 - eBay, Inc overview for young professionalsOnline Karrieretag Hamburg 2013 - eBay, Inc overview for young professionals
Online Karrieretag Hamburg 2013 - eBay, Inc overview for young professionals
 
REAL ESTATE BRAND BOOK 2015 mediadaten
REAL ESTATE BRAND BOOK 2015 mediadatenREAL ESTATE BRAND BOOK 2015 mediadaten
REAL ESTATE BRAND BOOK 2015 mediadaten
 
Designing The User Experience Curve 2.0
Designing The User Experience Curve 2.0Designing The User Experience Curve 2.0
Designing The User Experience Curve 2.0
 
Cloud Storage unter Berücksichtigung der Risiken von großen Datensammlungen a...
Cloud Storage unter Berücksichtigung der Risiken von großen Datensammlungen a...Cloud Storage unter Berücksichtigung der Risiken von großen Datensammlungen a...
Cloud Storage unter Berücksichtigung der Risiken von großen Datensammlungen a...
 
Social Media Conference Keynote
Social Media Conference KeynoteSocial Media Conference Keynote
Social Media Conference Keynote
 

Ähnlich wie Deep Learning @ ZHAW Datalab (with Mark Cieliebak & Yves Pauchard)

TechnicalBackgroundOverview
TechnicalBackgroundOverviewTechnicalBackgroundOverview
TechnicalBackgroundOverview
Motaz El-Saban
 

Ähnlich wie Deep Learning @ ZHAW Datalab (with Mark Cieliebak & Yves Pauchard) (20)

Deep Learning: a birds eye view
Deep Learning: a birds eye viewDeep Learning: a birds eye view
Deep Learning: a birds eye view
 
Transferring Software Testing Tools to Practice
Transferring Software Testing Tools to PracticeTransferring Software Testing Tools to Practice
Transferring Software Testing Tools to Practice
 
Introduction to deep learning
Introduction to deep learningIntroduction to deep learning
Introduction to deep learning
 
Deep Learning, an interactive introduction for NLP-ers
Deep Learning, an interactive introduction for NLP-ersDeep Learning, an interactive introduction for NLP-ers
Deep Learning, an interactive introduction for NLP-ers
 
Software Engineering Research: Leading a Double-Agent Life.
Software Engineering Research: Leading a Double-Agent Life.Software Engineering Research: Leading a Double-Agent Life.
Software Engineering Research: Leading a Double-Agent Life.
 
OWF14 - Big Data : The State of Machine Learning in 2014
OWF14 - Big Data : The State of Machine  Learning in 2014OWF14 - Big Data : The State of Machine  Learning in 2014
OWF14 - Big Data : The State of Machine Learning in 2014
 
Chocolate Flavoured Data Science
Chocolate Flavoured Data ScienceChocolate Flavoured Data Science
Chocolate Flavoured Data Science
 
The Concurrent Constraint Programming Research Programmes -- Redux
The Concurrent Constraint Programming Research Programmes -- ReduxThe Concurrent Constraint Programming Research Programmes -- Redux
The Concurrent Constraint Programming Research Programmes -- Redux
 
Data-X-v3.1
Data-X-v3.1Data-X-v3.1
Data-X-v3.1
 
Week1- Introduction.pptx
Week1- Introduction.pptxWeek1- Introduction.pptx
Week1- Introduction.pptx
 
NUS PhD e-open day 2020
NUS PhD e-open day 2020NUS PhD e-open day 2020
NUS PhD e-open day 2020
 
lecture1.pptx
lecture1.pptxlecture1.pptx
lecture1.pptx
 
The Opportunities and Challenges of Putting the Latest Computer Vision and De...
The Opportunities and Challenges of Putting the Latest Computer Vision and De...The Opportunities and Challenges of Putting the Latest Computer Vision and De...
The Opportunities and Challenges of Putting the Latest Computer Vision and De...
 
Data-X-Sparse-v2
Data-X-Sparse-v2Data-X-Sparse-v2
Data-X-Sparse-v2
 
Breaking Through The Challenges of Scalable Deep Learning for Video Analytics
Breaking Through The Challenges of Scalable Deep Learning for Video AnalyticsBreaking Through The Challenges of Scalable Deep Learning for Video Analytics
Breaking Through The Challenges of Scalable Deep Learning for Video Analytics
 
Mini Project- Face Recognition
Mini Project- Face RecognitionMini Project- Face Recognition
Mini Project- Face Recognition
 
TechnicalBackgroundOverview
TechnicalBackgroundOverviewTechnicalBackgroundOverview
TechnicalBackgroundOverview
 
Multi modal retrieval and generation with deep distributed models
Multi modal retrieval and generation with deep distributed modelsMulti modal retrieval and generation with deep distributed models
Multi modal retrieval and generation with deep distributed models
 
Deep Learning & NLP: Graphs to the Rescue!
Deep Learning & NLP: Graphs to the Rescue!Deep Learning & NLP: Graphs to the Rescue!
Deep Learning & NLP: Graphs to the Rescue!
 
Software Mining and Software Datasets
Software Mining and Software DatasetsSoftware Mining and Software Datasets
Software Mining and Software Datasets
 

Kürzlich hochgeladen

(May 9, 2024) Enhanced Ultrafast Vector Flow Imaging (VFI) Using Multi-Angle ...
(May 9, 2024) Enhanced Ultrafast Vector Flow Imaging (VFI) Using Multi-Angle ...(May 9, 2024) Enhanced Ultrafast Vector Flow Imaging (VFI) Using Multi-Angle ...
(May 9, 2024) Enhanced Ultrafast Vector Flow Imaging (VFI) Using Multi-Angle ...
Scintica Instrumentation
 
Phenolics: types, biosynthesis and functions.
Phenolics: types, biosynthesis and functions.Phenolics: types, biosynthesis and functions.
Phenolics: types, biosynthesis and functions.
Cherry
 
THE ROLE OF BIOTECHNOLOGY IN THE ECONOMIC UPLIFT.pptx
THE ROLE OF BIOTECHNOLOGY IN THE ECONOMIC UPLIFT.pptxTHE ROLE OF BIOTECHNOLOGY IN THE ECONOMIC UPLIFT.pptx
THE ROLE OF BIOTECHNOLOGY IN THE ECONOMIC UPLIFT.pptx
ANSARKHAN96
 
Biogenic Sulfur Gases as Biosignatures on Temperate Sub-Neptune Waterworlds
Biogenic Sulfur Gases as Biosignatures on Temperate Sub-Neptune WaterworldsBiogenic Sulfur Gases as Biosignatures on Temperate Sub-Neptune Waterworlds
Biogenic Sulfur Gases as Biosignatures on Temperate Sub-Neptune Waterworlds
Sérgio Sacani
 
POGONATUM : morphology, anatomy, reproduction etc.
POGONATUM : morphology, anatomy, reproduction etc.POGONATUM : morphology, anatomy, reproduction etc.
POGONATUM : morphology, anatomy, reproduction etc.
Cherry
 
development of diagnostic enzyme assay to detect leuser virus
development of diagnostic enzyme assay to detect leuser virusdevelopment of diagnostic enzyme assay to detect leuser virus
development of diagnostic enzyme assay to detect leuser virus
NazaninKarimi6
 

Kürzlich hochgeladen (20)

Thyroid Physiology_Dr.E. Muralinath_ Associate Professor
Thyroid Physiology_Dr.E. Muralinath_ Associate ProfessorThyroid Physiology_Dr.E. Muralinath_ Associate Professor
Thyroid Physiology_Dr.E. Muralinath_ Associate Professor
 
Site specific recombination and transposition.........pdf
Site specific recombination and transposition.........pdfSite specific recombination and transposition.........pdf
Site specific recombination and transposition.........pdf
 
(May 9, 2024) Enhanced Ultrafast Vector Flow Imaging (VFI) Using Multi-Angle ...
(May 9, 2024) Enhanced Ultrafast Vector Flow Imaging (VFI) Using Multi-Angle ...(May 9, 2024) Enhanced Ultrafast Vector Flow Imaging (VFI) Using Multi-Angle ...
(May 9, 2024) Enhanced Ultrafast Vector Flow Imaging (VFI) Using Multi-Angle ...
 
Plasmid: types, structure and functions.
Plasmid: types, structure and functions.Plasmid: types, structure and functions.
Plasmid: types, structure and functions.
 
Concept of gene and Complementation test.pdf
Concept of gene and Complementation test.pdfConcept of gene and Complementation test.pdf
Concept of gene and Complementation test.pdf
 
Phenolics: types, biosynthesis and functions.
Phenolics: types, biosynthesis and functions.Phenolics: types, biosynthesis and functions.
Phenolics: types, biosynthesis and functions.
 
THE ROLE OF BIOTECHNOLOGY IN THE ECONOMIC UPLIFT.pptx
THE ROLE OF BIOTECHNOLOGY IN THE ECONOMIC UPLIFT.pptxTHE ROLE OF BIOTECHNOLOGY IN THE ECONOMIC UPLIFT.pptx
THE ROLE OF BIOTECHNOLOGY IN THE ECONOMIC UPLIFT.pptx
 
PATNA CALL GIRLS 8617370543 LOW PRICE ESCORT SERVICE
PATNA CALL GIRLS 8617370543 LOW PRICE ESCORT SERVICEPATNA CALL GIRLS 8617370543 LOW PRICE ESCORT SERVICE
PATNA CALL GIRLS 8617370543 LOW PRICE ESCORT SERVICE
 
module for grade 9 for distance learning
module for grade 9 for distance learningmodule for grade 9 for distance learning
module for grade 9 for distance learning
 
Gwalior ❤CALL GIRL 84099*07087 ❤CALL GIRLS IN Gwalior ESCORT SERVICE❤CALL GIRL
Gwalior ❤CALL GIRL 84099*07087 ❤CALL GIRLS IN Gwalior ESCORT SERVICE❤CALL GIRLGwalior ❤CALL GIRL 84099*07087 ❤CALL GIRLS IN Gwalior ESCORT SERVICE❤CALL GIRL
Gwalior ❤CALL GIRL 84099*07087 ❤CALL GIRLS IN Gwalior ESCORT SERVICE❤CALL GIRL
 
Cot curve, melting temperature, unique and repetitive DNA
Cot curve, melting temperature, unique and repetitive DNACot curve, melting temperature, unique and repetitive DNA
Cot curve, melting temperature, unique and repetitive DNA
 
Biogenic Sulfur Gases as Biosignatures on Temperate Sub-Neptune Waterworlds
Biogenic Sulfur Gases as Biosignatures on Temperate Sub-Neptune WaterworldsBiogenic Sulfur Gases as Biosignatures on Temperate Sub-Neptune Waterworlds
Biogenic Sulfur Gases as Biosignatures on Temperate Sub-Neptune Waterworlds
 
Terpineol and it's characterization pptx
Terpineol and it's characterization pptxTerpineol and it's characterization pptx
Terpineol and it's characterization pptx
 
Dr. E. Muralinath_ Blood indices_clinical aspects
Dr. E. Muralinath_ Blood indices_clinical  aspectsDr. E. Muralinath_ Blood indices_clinical  aspects
Dr. E. Muralinath_ Blood indices_clinical aspects
 
Genetics and epigenetics of ADHD and comorbid conditions
Genetics and epigenetics of ADHD and comorbid conditionsGenetics and epigenetics of ADHD and comorbid conditions
Genetics and epigenetics of ADHD and comorbid conditions
 
Genome sequencing,shotgun sequencing.pptx
Genome sequencing,shotgun sequencing.pptxGenome sequencing,shotgun sequencing.pptx
Genome sequencing,shotgun sequencing.pptx
 
Site Acceptance Test .
Site Acceptance Test                    .Site Acceptance Test                    .
Site Acceptance Test .
 
POGONATUM : morphology, anatomy, reproduction etc.
POGONATUM : morphology, anatomy, reproduction etc.POGONATUM : morphology, anatomy, reproduction etc.
POGONATUM : morphology, anatomy, reproduction etc.
 
development of diagnostic enzyme assay to detect leuser virus
development of diagnostic enzyme assay to detect leuser virusdevelopment of diagnostic enzyme assay to detect leuser virus
development of diagnostic enzyme assay to detect leuser virus
 
CURRENT SCENARIO OF POULTRY PRODUCTION IN INDIA
CURRENT SCENARIO OF POULTRY PRODUCTION IN INDIACURRENT SCENARIO OF POULTRY PRODUCTION IN INDIA
CURRENT SCENARIO OF POULTRY PRODUCTION IN INDIA
 

Deep Learning @ ZHAW Datalab (with Mark Cieliebak & Yves Pauchard)

  • 1. Zürcher Fachhochschule Deep Learning @ ZHAW Thilo Stadelmann, Mark Cieliebak & Yves Pauchard InIT Colloquium, 15. April 2015, Winterthur
  • 2. Zürcher Fachhochschule 2 Agenda Overview • What is Deep Learning? ‘15 • Our stake in it InIT Use Case: Text Analytics ‘10 • InIT Use Case: Face Recognition ‘10 •
  • 4. Zürcher Fachhochschule 4 Deep Learning is… …Continued Neural Network Research What’s new? • Novel architectures (wider, deeper) • Faster and better training (e.g., understanding of Backpropagation’s “vanishing gradient” problem, good initial weights) • Better regularization (e.g., Dropout, Max-pooling etc.) • Big Data (or augmentation) and corresponding computational power on GPUs  «Add as many parameters as possible for your hardware and train the hell out of it with proper regularization» (Yann LeCun)
  • 5. Zürcher Fachhochschule 5 Deep Learning is… … Successful Areas of successful application: • Computer Vision (detection, segmentation, recognition, OCR, video analysis) • Speech Processing (Recognition, Siri etc.) • Natural Language Processing (Translation, Sentiment Analysis) • Metric Learning (distances, invariances, hashing) • Prediction & Forecasting (financial, time series) Red titled slides by Jonathan Masci
  • 6. Zürcher Fachhochschule 6 Technical Idea Learning Features, not just rules Hand-engineering features is tedious  Let each layer learn a new representation of the data by itself Actual learning is… • governed by the learning target (input-output pairs & objective function), • facilitated by constraints & regularizations (e.g., sparsity to learn distributed codes), • enforced by the Backpropagation algorithm (1970-1989) What is learned? • Highly non-linear functions purely from data • Hierarchies of features, combinations of elements (distributed codes) State of the Art • CNNs (Convolutional Neural Networks) for vision tasks and beyond  Relatively easy to use, very successful, biologically inspired, broad user basis • RNNs (Recurrent Neural networks) for sequences and hard tasks  Turing complete, hot research topic Honglak Lee, University of Michigan Yan et al., National University of Singapore
  • 7. Zürcher Fachhochschule 7 The Deep Learning Market … and what we do about it! Strategic relevance • 3 years ago: <10 research groups at «ivy league» universities • 01/2014: Google acquires DeepMind for 500 Mio. $ (startup by IDSIA / Ticino) • Currently: • Courses / books / software frameworks are all «beta versions» • Boundaries between research and application are strongly domain-specific • Outlook: Could be a tool like «SVM» in 2-5 years Deep Learning @ Datalab • Hardware invests: 2 multi-GPU Workstations http://www.zhaw.ch/de/zhaw/institute-zentren/uebergreifende-institute-zentren/dlab/hardware.html • People invests: 13 researchers formed the Deep Learning Journals Club in 2014 deeplearning@downbirn.zhaw.ch • Projects: • 2 internal projects finished (see use cases later!) • 2 CTI projects just got funded (start this summer) • Several proposals pending
  • 8. Zürcher Fachhochschule 8 Use Case «Text Analytics» Mark Cieliebak 
  • 9. Zürcher Fachhochschule 9 Goal: Turn text into information Sentiment Analysis Q&A Named Entity Extraction Text Summarization Machine Translation Spelling Correction Information Retrieval What is "Text Analytics"?
  • 10. Zürcher Fachhochschule 10 Rule-Based Corpus-Based Deep Learning Predicted Label Approaches to Text Analytics
  • 12. Zürcher Fachhochschule 12 Sample Features for Tweets Word ngrams: presence or absence of contiguous sequences of 1, 2, 3, and 4 tokens; noncontiguous ngrams POS: the number of occurrences of each part-of-speech tag Sentiment Lexica: each word annotated with tonality score (-1..0..+1) Negation: the number of negated contexts Punctuation: the number of contiguous sequences of exclamation marks, question marks, and both exclamation and question marks Emoticons: presence or absence, last token is a positive or negative emoticon; Hashtags: the number of hashtags; Elongated words: the number of words with one character repeated (e.g. ‘soooo’) from: Mohammad et al., SemEval 2013
  • 13. Zürcher Fachhochschule 13 Feature-Based Text Analytics Most Important Issues • Requires large annotated corpora • Depends on good features [6]
  • 14. Zürcher Fachhochschule 14 Deep Learning on Text Deep Learning: It's all about Word Vectors!
  • 15. Zürcher Fachhochschule 15 Word2Vec • Huge set of text samples (billions of words) • Extract dictionary • Word-Matrix: k-dimensional vector for each word (k typically 50-500) • Word vector initialized randomly • Train word vectors to predict next words, given a sequence of words from sample text Major contributions by Bengio et al. 2003, Collobert&Weston 2008, Socher et al. 2011, Mikolov et al. 2013
  • 16. Zürcher Fachhochschule 16 The Magic of Word Vectors King - Man + Woman ≈ Queen Live Demo on 100b words from Google News dataset: http://radimrehurek.com/2014/02/word2vec-tutorial/
  • 18. Zürcher Fachhochschule 18 Using Word Vectors in NLP Collobert et al., 2011: • SENNA: Generic NLP System based on word vectors • Solves many NLP-Tasks as good as benchmark systems
  • 19. Zürcher Fachhochschule 19 Sentiment Analysis "… WiFi Analytics is a free Android app that I find very handy when it comes to troubleshooting and monitoring a home network. "
  • 20. Zürcher Fachhochschule 20 Deep Learning and Sentiment • Maas et al., 2011: word vectors with sentiment context • Socher et al, 2013: Representing sentence structures as trees with sentiment annotation • Quoc and Mikolov, 2014: "Paragraph Vectors" wonderful terrible amazing awful
  • 21. Zürcher Fachhochschule 21 Words and Images Untrained Class Demo: http://www.clarifai.com/#demo
  • 22. Zürcher Fachhochschule 22 Use Case «Face Recognition» Yves Pauchard 
  • 23. Zürcher Fachhochschule 23 piVision: Face recognition on a Raspberry Pi
  • 24. Zürcher Fachhochschule 24 What is face recognition? Detection: Is this a face or not? Verification: Are these two pictures showing the same face? Identification: Is this Yves?
  • 25. Zürcher Fachhochschule 25 Pipeline Detect Align Feature extractor Train Pre-processor Model Filter Recognizer Predict Extract face Correct pose Correct illumination Dimensionality reduction Classification
  • 26. Zürcher Fachhochschule 26 Software development • Python (OpenCV) + PyCharm + SVN + TeamCity (Raspberry Pi and Linux agents) • Timing and accuracy test after each commit
  • 27. Zürcher Fachhochschule 27 Baseline: Fisherfaces (OpenCV) Detect Align Feature extractor Train Pre-processor Model Filter Recognizer Predict Viola & Jones 2D similarity transform Gamma + DoG Principal Component Analysis Linear Discriminate Analysis
  • 28. Zürcher Fachhochschule 28 Deep Learning Detect Align Feature extractor Train Pre-processor Model Filter Recognizer Predict Viola & Jones Local binary pattern + ellipse Convolutional Neural Network: Features are learned
  • 29. Zürcher Fachhochschule 29 Experiment Testing outdoors (used exclusively for testing) Training indoors (used for learning) Approx. 40 images of 6 individuals acquired in 2 batches. For CNN training, an augmented set was used, i.e. additional training images were synthetically created.
  • 31. Zürcher Fachhochschule 31 Interesting findings • Alignment is crucial for baseline algorithm – time consuming • CNN needs to be trained on desktop PC with GPU • Training data augmentation for CNN can effectively replace the alignment step – saving time • CNN outperforms baseline algorithm 99.6 % : 96.9 %, dropping less images and saving time. • Let’s see it running: https://www.youtube.com/watch?v=oI1eJa-UWNU
  • 32. Zürcher Fachhochschule 32 Further Reading • Very brief history with some links (2015) http://dublin.zhaw.ch/~stdm/?p=241 • Comprehensive history & survey (2015) Schmidhuber, “Deep Learning in Neural Networks: An Overview” http://arxiv.org/abs/1404.7828 • Deep Learning Kick-off (2006  of historical interest) Hinton et al., “A Fast Learning Algorithm for Deep Belief Nets” http://www.cs.toronto.edu/~hinton/absps/ncfast.pdf • Very practical overview of Convolutional Neural Networks (CNNs, 1998) LeCun et al., “Gradient-Based Learning Applied to Document Recognition” http://yann.lecun.com/exdb/publis/pdf/lecun-98.pdf • Cool application for which Google paid 500 Mio. $ (2015) Mnih et al, “Human-Level Control through Deep Reinforcement Learning” http://www.nature.com/nature/journal/v518/n7540/full/nature14236.html