SlideShare a Scribd company logo
The image part with relationship ID rId14 was not found in the file.
{
Deep  Learning
And  Its  Applications:  Computer  Vision
Adam  Gibson
{  deeplearning4j.org  //  skymind.io  //  zipfian  academy
The image part with relationship ID rId14 was not found in the file.
•  Object  Recognition
•  Image  Categorization
•  Scene  Parsing
•  Face  Recognition
Computer  Vision:  A  Primer
The image part with relationship ID rId14 was not found in the file.
•  OpenCV  
•  SIFT
•  Filters/Edge  Detection
•  Feature  Extraction
What’s  currently  done?
The image part with relationship ID rId14 was not found in the file.
•  Representation  Learning  
•  More  precise  than  hand-­‐‑done  
features
•  Non-­‐‑linearities  and  higher-­‐‑order  
trends
•  Pretrain  and  Hessian  Free
This  is  manual!
The image part with relationship ID rId14 was not found in the file.
•  Representation  Learning
•  Position  Invariance  with  convolutions
•  Semantic  Hashing  
Deep  Learning  and  Images
The image part with relationship ID rId14 was not found in the file.
•  Normal  pixels  –  0-­‐‑255  –  
normalization
•  Sparse  –  binarization  (depending  on  
pixel  presence)
Different  kinds  of  images
The image part with relationship ID rId14 was not found in the file.
•  Faces  =  a  collection  of  images.
•  With  persistent  pa_erns  of  pixels.
•  Pixel  pa_erns  =  features.
•  Nets  learn  to  identify  features  in  data,  to  
classify  faces  as  faces  and  label  them:  John  or  
Sarah.
•  Nets  train  by  reconstructing  faces  from  features  
many  times.	
•  Measuring  their  work  against  a  benchmark.
Facial  recognition
The image part with relationship ID rId14 was not found in the file.
DL4J’s  Facial  Reconstructions
The image part with relationship ID rId14 was not found in the file.
•  Slices  of  a  feature  space  (Max  pooling)	
•  Learns  different  portions  for  easily  scalable  
and  robust  feature  engineering.	
Position  Invariance  -­‐‑  Convolutions
The image part with relationship ID rId14 was not found in the file.
Visual  Example  -­‐‑  Convolutions
The image part with relationship ID rId14 was not found in the file.
Pen  Strokes
The image part with relationship ID rId14 was not found in the file.
•  Facebook  uses  facial  recognition  to  make  
itself  stickier  and  know  more  about  us.
•  Government  agencies  use  it  to  secure  
national  borders.
•  Video  game  makers  use  it  to  construct  more  
realistic  worlds.
•  Stores  use  it  to  identify  customers  and  track  
behavior.
What  are  faces  for?
The image part with relationship ID rId14 was not found in the file.
•  2  layers  of  neuron-­‐‑like  nodes.	
•  The  1st  is  the  visible,  or  input,  layer	
•  The  2nd  is  “hidden.”  It  identifies  features  in  input	
•  Symmetrically  connected.	
•  “Restricted”  =  no  visible-­‐‑visible  or  hidden-­‐‑hidden  
ties	
•  All  connections  happen  between  layers.	
Restricted  Bolgmann  
Machines  (RBMs)
The image part with relationship ID rId14 was not found in the file.
•  A  stack  of  RBMs.	
•  Each  RBM’s  hidden  layer  à  Next  RBM’s  visible/input  
layer.  	
•  DBNs  learn  more  &  more  complex  features	
•  Example:  	
•  1)  Pixels  =  input;  	
•  2)  H1  learns  an  edge  or  line;  	
•  3)  H2  learns  a  corner  or  set  of  lines;  	
•  4)  H3  learns  two  groups  of  lines  forming  an  object  
-­‐‑-­‐‑  a  face!	
•  Final  layer  classifies  feature  groups:  sunset,  elephant,  
flower,  John,  Sarah.	
Deep-­‐‑Belief  Net  (DBN)
The image part with relationship ID rId14 was not found in the file.
•  2  DBNs.
•  1st  DBN  *encodes*  data  into  vector  of  10-­‐‑30  
numbers  =  Pre-­‐‑training.
•  2nd  DBN  decodes  data  into  original  state.
•  Backprop  only  happens  on  2nd  DBN
•  2nd  is  the  fine-­‐‑tuning  stage  (reconstruction  entropy).
•  Reduces  documents  or  images  to  compact  vectors  .
•  Useful  in  search,  QA  and  information  retrieval.
Deep  Autoencoder
The image part with relationship ID rId14 was not found in the file.
Deep  Autoencoder  Architecture
The image part with relationship ID rId14 was not found in the file.
Image  Search  Results
The image part with relationship ID rId14 was not found in the file.
•  Top-­‐‑down  &  hierarchical  rather  than  feed-­‐‑forward  (DBNs).
•  Handles  sequence-­‐‑based  classification,  windows  of  several  
events,  entire  scenes  (multiple  objects).
•  Features  themselves  are  vectors.  
•  A  tensor  =  a  multi-­‐‑dimensional  matrix,  or  multiple  matrices  of  
the  same  size.
Recursive  Neural  Tensor  Net
The image part with relationship ID rId14 was not found in the file.
RNTNs  &  Scene  Composition

More Related Content

Viewers also liked

General introduction to computer vision
General introduction to computer visionGeneral introduction to computer vision
General introduction to computer vision
butest
 
Computer Vision
Computer VisionComputer Vision
Computer Vision
Nitin Sharma
 
Computer vision
Computer visionComputer vision
Computer vision
Kartik Kalpande Patil
 
COM2304: Introduction to Computer Vision & Image Processing
COM2304: Introduction to Computer Vision & Image Processing COM2304: Introduction to Computer Vision & Image Processing
COM2304: Introduction to Computer Vision & Image Processing
Hemantha Kulathilake
 
Nonverbal
NonverbalNonverbal
Nonverbal
ravi kant
 
Computer Vision Introduction
Computer Vision IntroductionComputer Vision Introduction
Computer Vision Introduction
Camera Culture Group, MIT Media Lab
 
Cross platform computer vision optimization
Cross platform computer vision optimizationCross platform computer vision optimization
Cross platform computer vision optimization
Yoss Cohen
 
Understanding hearing impairment
Understanding hearing impairmentUnderstanding hearing impairment
Understanding hearing impairment
Den Osmena
 
Deaf culture
Deaf cultureDeaf culture
Deaf culture
Christine Sharkey
 
Sign Language in Communication
Sign Language in CommunicationSign Language in Communication
Sign Language in Communication
Meera Hapaliya
 
Sign Language
Sign LanguageSign Language
Sign Language
Hegi Soosaar
 
Matrix and Tensor Tools for Computer Vision
Matrix and Tensor Tools for Computer VisionMatrix and Tensor Tools for Computer Vision
Matrix and Tensor Tools for Computer Vision
ActiveEon
 
Computer Vision
Computer VisionComputer Vision
Computer Vision
Ameer Mohamed Rajah
 
Hearing impairment
Hearing impairmentHearing impairment
Hearing impairment
butterbear
 
Dbms Project
Dbms ProjectDbms Project
Dbms Project
sana khalid
 
American Sign Language
American Sign LanguageAmerican Sign Language
American Sign Language
Brittany Johnston
 
What Is Sign Language
What Is Sign LanguageWhat Is Sign Language
What Is Sign Language
Arun Rao
 
Sign language ppt
Sign language pptSign language ppt
Sign language ppt
Amina Magaji
 
Image processing ppt
Image processing pptImage processing ppt
Image processing ppt
Raviteja Chowdary Adusumalli
 
applications of computer graphics
applications of computer graphicsapplications of computer graphics
applications of computer graphics
Aaina Katyal
 

Viewers also liked (20)

General introduction to computer vision
General introduction to computer visionGeneral introduction to computer vision
General introduction to computer vision
 
Computer Vision
Computer VisionComputer Vision
Computer Vision
 
Computer vision
Computer visionComputer vision
Computer vision
 
COM2304: Introduction to Computer Vision & Image Processing
COM2304: Introduction to Computer Vision & Image Processing COM2304: Introduction to Computer Vision & Image Processing
COM2304: Introduction to Computer Vision & Image Processing
 
Nonverbal
NonverbalNonverbal
Nonverbal
 
Computer Vision Introduction
Computer Vision IntroductionComputer Vision Introduction
Computer Vision Introduction
 
Cross platform computer vision optimization
Cross platform computer vision optimizationCross platform computer vision optimization
Cross platform computer vision optimization
 
Understanding hearing impairment
Understanding hearing impairmentUnderstanding hearing impairment
Understanding hearing impairment
 
Deaf culture
Deaf cultureDeaf culture
Deaf culture
 
Sign Language in Communication
Sign Language in CommunicationSign Language in Communication
Sign Language in Communication
 
Sign Language
Sign LanguageSign Language
Sign Language
 
Matrix and Tensor Tools for Computer Vision
Matrix and Tensor Tools for Computer VisionMatrix and Tensor Tools for Computer Vision
Matrix and Tensor Tools for Computer Vision
 
Computer Vision
Computer VisionComputer Vision
Computer Vision
 
Hearing impairment
Hearing impairmentHearing impairment
Hearing impairment
 
Dbms Project
Dbms ProjectDbms Project
Dbms Project
 
American Sign Language
American Sign LanguageAmerican Sign Language
American Sign Language
 
What Is Sign Language
What Is Sign LanguageWhat Is Sign Language
What Is Sign Language
 
Sign language ppt
Sign language pptSign language ppt
Sign language ppt
 
Image processing ppt
Image processing pptImage processing ppt
Image processing ppt
 
applications of computer graphics
applications of computer graphicsapplications of computer graphics
applications of computer graphics
 

More from Adam Gibson

End to end MLworkflows
End to end MLworkflowsEnd to end MLworkflows
End to end MLworkflows
Adam Gibson
 
World Artificial Intelligence Conference Shanghai 2018
World Artificial Intelligence Conference Shanghai 2018World Artificial Intelligence Conference Shanghai 2018
World Artificial Intelligence Conference Shanghai 2018
Adam Gibson
 
Deploying signature verification with deep learning
Deploying signature verification with deep learningDeploying signature verification with deep learning
Deploying signature verification with deep learning
Adam Gibson
 
Self driving computers active learning workflows with human interpretable ve...
Self driving computers  active learning workflows with human interpretable ve...Self driving computers  active learning workflows with human interpretable ve...
Self driving computers active learning workflows with human interpretable ve...
Adam Gibson
 
Anomaly Detection and Automatic Labeling with Deep Learning
Anomaly Detection and Automatic Labeling with Deep LearningAnomaly Detection and Automatic Labeling with Deep Learning
Anomaly Detection and Automatic Labeling with Deep Learning
Adam Gibson
 
Strata Beijing 2017: Jumpy, a python interface for nd4j
Strata Beijing 2017: Jumpy, a python interface for nd4jStrata Beijing 2017: Jumpy, a python interface for nd4j
Strata Beijing 2017: Jumpy, a python interface for nd4j
Adam Gibson
 
Boolan machine learning summit
Boolan machine learning summitBoolan machine learning summit
Boolan machine learning summit
Adam Gibson
 
Advanced deeplearning4j features
Advanced deeplearning4j featuresAdvanced deeplearning4j features
Advanced deeplearning4j features
Adam Gibson
 
Deep Learning with GPUs in Production - AI By the Bay
Deep Learning with GPUs in Production - AI By the BayDeep Learning with GPUs in Production - AI By the Bay
Deep Learning with GPUs in Production - AI By the Bay
Adam Gibson
 
Big Data Analytics Tokyo
Big Data Analytics TokyoBig Data Analytics Tokyo
Big Data Analytics Tokyo
Adam Gibson
 
Wrangleconf Big Data Malaysia 2016
Wrangleconf Big Data Malaysia 2016Wrangleconf Big Data Malaysia 2016
Wrangleconf Big Data Malaysia 2016
Adam Gibson
 
Distributed deep rl on spark strata singapore
Distributed deep rl on spark   strata singaporeDistributed deep rl on spark   strata singapore
Distributed deep rl on spark strata singapore
Adam Gibson
 
Deep learning in production with the best
Deep learning in production   with the bestDeep learning in production   with the best
Deep learning in production with the best
Adam Gibson
 
Dl4j in the wild
Dl4j in the wildDl4j in the wild
Dl4j in the wild
Adam Gibson
 
SKIL - Dl4j in the wild meetup
SKIL - Dl4j in the wild meetupSKIL - Dl4j in the wild meetup
SKIL - Dl4j in the wild meetup
Adam Gibson
 
Strata Beijing - Deep Learning in Production on Spark
Strata Beijing - Deep Learning in Production on SparkStrata Beijing - Deep Learning in Production on Spark
Strata Beijing - Deep Learning in Production on Spark
Adam Gibson
 
Anomaly detection in deep learning (Updated) English
Anomaly detection in deep learning (Updated) EnglishAnomaly detection in deep learning (Updated) English
Anomaly detection in deep learning (Updated) English
Adam Gibson
 
Skymind - Udacity China presentation
Skymind - Udacity China presentationSkymind - Udacity China presentation
Skymind - Udacity China presentation
Adam Gibson
 
Anomaly Detection in Deep Learning (Updated)
Anomaly Detection in Deep Learning (Updated)Anomaly Detection in Deep Learning (Updated)
Anomaly Detection in Deep Learning (Updated)
Adam Gibson
 
Hadoop summit 2016
Hadoop summit 2016Hadoop summit 2016
Hadoop summit 2016
Adam Gibson
 

More from Adam Gibson (20)

End to end MLworkflows
End to end MLworkflowsEnd to end MLworkflows
End to end MLworkflows
 
World Artificial Intelligence Conference Shanghai 2018
World Artificial Intelligence Conference Shanghai 2018World Artificial Intelligence Conference Shanghai 2018
World Artificial Intelligence Conference Shanghai 2018
 
Deploying signature verification with deep learning
Deploying signature verification with deep learningDeploying signature verification with deep learning
Deploying signature verification with deep learning
 
Self driving computers active learning workflows with human interpretable ve...
Self driving computers  active learning workflows with human interpretable ve...Self driving computers  active learning workflows with human interpretable ve...
Self driving computers active learning workflows with human interpretable ve...
 
Anomaly Detection and Automatic Labeling with Deep Learning
Anomaly Detection and Automatic Labeling with Deep LearningAnomaly Detection and Automatic Labeling with Deep Learning
Anomaly Detection and Automatic Labeling with Deep Learning
 
Strata Beijing 2017: Jumpy, a python interface for nd4j
Strata Beijing 2017: Jumpy, a python interface for nd4jStrata Beijing 2017: Jumpy, a python interface for nd4j
Strata Beijing 2017: Jumpy, a python interface for nd4j
 
Boolan machine learning summit
Boolan machine learning summitBoolan machine learning summit
Boolan machine learning summit
 
Advanced deeplearning4j features
Advanced deeplearning4j featuresAdvanced deeplearning4j features
Advanced deeplearning4j features
 
Deep Learning with GPUs in Production - AI By the Bay
Deep Learning with GPUs in Production - AI By the BayDeep Learning with GPUs in Production - AI By the Bay
Deep Learning with GPUs in Production - AI By the Bay
 
Big Data Analytics Tokyo
Big Data Analytics TokyoBig Data Analytics Tokyo
Big Data Analytics Tokyo
 
Wrangleconf Big Data Malaysia 2016
Wrangleconf Big Data Malaysia 2016Wrangleconf Big Data Malaysia 2016
Wrangleconf Big Data Malaysia 2016
 
Distributed deep rl on spark strata singapore
Distributed deep rl on spark   strata singaporeDistributed deep rl on spark   strata singapore
Distributed deep rl on spark strata singapore
 
Deep learning in production with the best
Deep learning in production   with the bestDeep learning in production   with the best
Deep learning in production with the best
 
Dl4j in the wild
Dl4j in the wildDl4j in the wild
Dl4j in the wild
 
SKIL - Dl4j in the wild meetup
SKIL - Dl4j in the wild meetupSKIL - Dl4j in the wild meetup
SKIL - Dl4j in the wild meetup
 
Strata Beijing - Deep Learning in Production on Spark
Strata Beijing - Deep Learning in Production on SparkStrata Beijing - Deep Learning in Production on Spark
Strata Beijing - Deep Learning in Production on Spark
 
Anomaly detection in deep learning (Updated) English
Anomaly detection in deep learning (Updated) EnglishAnomaly detection in deep learning (Updated) English
Anomaly detection in deep learning (Updated) English
 
Skymind - Udacity China presentation
Skymind - Udacity China presentationSkymind - Udacity China presentation
Skymind - Udacity China presentation
 
Anomaly Detection in Deep Learning (Updated)
Anomaly Detection in Deep Learning (Updated)Anomaly Detection in Deep Learning (Updated)
Anomaly Detection in Deep Learning (Updated)
 
Hadoop summit 2016
Hadoop summit 2016Hadoop summit 2016
Hadoop summit 2016
 

Recently uploaded

Unit-III-ELECTROCHEMICAL STORAGE DEVICES.ppt
Unit-III-ELECTROCHEMICAL STORAGE DEVICES.pptUnit-III-ELECTROCHEMICAL STORAGE DEVICES.ppt
Unit-III-ELECTROCHEMICAL STORAGE DEVICES.ppt
KrishnaveniKrishnara1
 
哪里办理(csu毕业证书)查尔斯特大学毕业证硕士学历原版一模一样
哪里办理(csu毕业证书)查尔斯特大学毕业证硕士学历原版一模一样哪里办理(csu毕业证书)查尔斯特大学毕业证硕士学历原版一模一样
哪里办理(csu毕业证书)查尔斯特大学毕业证硕士学历原版一模一样
insn4465
 
Harnessing WebAssembly for Real-time Stateless Streaming Pipelines
Harnessing WebAssembly for Real-time Stateless Streaming PipelinesHarnessing WebAssembly for Real-time Stateless Streaming Pipelines
Harnessing WebAssembly for Real-time Stateless Streaming Pipelines
Christina Lin
 
Embedded machine learning-based road conditions and driving behavior monitoring
Embedded machine learning-based road conditions and driving behavior monitoringEmbedded machine learning-based road conditions and driving behavior monitoring
Embedded machine learning-based road conditions and driving behavior monitoring
IJECEIAES
 
Modelagem de um CSTR com reação endotermica.pdf
Modelagem de um CSTR com reação endotermica.pdfModelagem de um CSTR com reação endotermica.pdf
Modelagem de um CSTR com reação endotermica.pdf
camseq
 
Presentation of IEEE Slovenia CIS (Computational Intelligence Society) Chapte...
Presentation of IEEE Slovenia CIS (Computational Intelligence Society) Chapte...Presentation of IEEE Slovenia CIS (Computational Intelligence Society) Chapte...
Presentation of IEEE Slovenia CIS (Computational Intelligence Society) Chapte...
University of Maribor
 
ML Based Model for NIDS MSc Updated Presentation.v2.pptx
ML Based Model for NIDS MSc Updated Presentation.v2.pptxML Based Model for NIDS MSc Updated Presentation.v2.pptx
ML Based Model for NIDS MSc Updated Presentation.v2.pptx
JamalHussainArman
 
spirit beverages ppt without graphics.pptx
spirit beverages ppt without graphics.pptxspirit beverages ppt without graphics.pptx
spirit beverages ppt without graphics.pptx
Madan Karki
 
Question paper of renewable energy sources
Question paper of renewable energy sourcesQuestion paper of renewable energy sources
Question paper of renewable energy sources
mahammadsalmanmech
 
学校原版美国波士顿大学毕业证学历学位证书原版一模一样
学校原版美国波士顿大学毕业证学历学位证书原版一模一样学校原版美国波士顿大学毕业证学历学位证书原版一模一样
学校原版美国波士顿大学毕业证学历学位证书原版一模一样
171ticu
 
basic-wireline-operations-course-mahmoud-f-radwan.pdf
basic-wireline-operations-course-mahmoud-f-radwan.pdfbasic-wireline-operations-course-mahmoud-f-radwan.pdf
basic-wireline-operations-course-mahmoud-f-radwan.pdf
NidhalKahouli2
 
22CYT12-Unit-V-E Waste and its Management.ppt
22CYT12-Unit-V-E Waste and its Management.ppt22CYT12-Unit-V-E Waste and its Management.ppt
22CYT12-Unit-V-E Waste and its Management.ppt
KrishnaveniKrishnara1
 
2008 BUILDING CONSTRUCTION Illustrated - Ching Chapter 02 The Building.pdf
2008 BUILDING CONSTRUCTION Illustrated - Ching Chapter 02 The Building.pdf2008 BUILDING CONSTRUCTION Illustrated - Ching Chapter 02 The Building.pdf
2008 BUILDING CONSTRUCTION Illustrated - Ching Chapter 02 The Building.pdf
Yasser Mahgoub
 
Engine Lubrication performance System.pdf
Engine Lubrication performance System.pdfEngine Lubrication performance System.pdf
Engine Lubrication performance System.pdf
mamamaam477
 
官方认证美国密歇根州立大学毕业证学位证书原版一模一样
官方认证美国密歇根州立大学毕业证学位证书原版一模一样官方认证美国密歇根州立大学毕业证学位证书原版一模一样
官方认证美国密歇根州立大学毕业证学位证书原版一模一样
171ticu
 
Iron and Steel Technology Roadmap - Towards more sustainable steelmaking.pdf
Iron and Steel Technology Roadmap - Towards more sustainable steelmaking.pdfIron and Steel Technology Roadmap - Towards more sustainable steelmaking.pdf
Iron and Steel Technology Roadmap - Towards more sustainable steelmaking.pdf
RadiNasr
 
A review on techniques and modelling methodologies used for checking electrom...
A review on techniques and modelling methodologies used for checking electrom...A review on techniques and modelling methodologies used for checking electrom...
A review on techniques and modelling methodologies used for checking electrom...
nooriasukmaningtyas
 
Advanced control scheme of doubly fed induction generator for wind turbine us...
Advanced control scheme of doubly fed induction generator for wind turbine us...Advanced control scheme of doubly fed induction generator for wind turbine us...
Advanced control scheme of doubly fed induction generator for wind turbine us...
IJECEIAES
 
Casting-Defect-inSlab continuous casting.pdf
Casting-Defect-inSlab continuous casting.pdfCasting-Defect-inSlab continuous casting.pdf
Casting-Defect-inSlab continuous casting.pdf
zubairahmad848137
 
Engineering Drawings Lecture Detail Drawings 2014.pdf
Engineering Drawings Lecture Detail Drawings 2014.pdfEngineering Drawings Lecture Detail Drawings 2014.pdf
Engineering Drawings Lecture Detail Drawings 2014.pdf
abbyasa1014
 

Recently uploaded (20)

Unit-III-ELECTROCHEMICAL STORAGE DEVICES.ppt
Unit-III-ELECTROCHEMICAL STORAGE DEVICES.pptUnit-III-ELECTROCHEMICAL STORAGE DEVICES.ppt
Unit-III-ELECTROCHEMICAL STORAGE DEVICES.ppt
 
哪里办理(csu毕业证书)查尔斯特大学毕业证硕士学历原版一模一样
哪里办理(csu毕业证书)查尔斯特大学毕业证硕士学历原版一模一样哪里办理(csu毕业证书)查尔斯特大学毕业证硕士学历原版一模一样
哪里办理(csu毕业证书)查尔斯特大学毕业证硕士学历原版一模一样
 
Harnessing WebAssembly for Real-time Stateless Streaming Pipelines
Harnessing WebAssembly for Real-time Stateless Streaming PipelinesHarnessing WebAssembly for Real-time Stateless Streaming Pipelines
Harnessing WebAssembly for Real-time Stateless Streaming Pipelines
 
Embedded machine learning-based road conditions and driving behavior monitoring
Embedded machine learning-based road conditions and driving behavior monitoringEmbedded machine learning-based road conditions and driving behavior monitoring
Embedded machine learning-based road conditions and driving behavior monitoring
 
Modelagem de um CSTR com reação endotermica.pdf
Modelagem de um CSTR com reação endotermica.pdfModelagem de um CSTR com reação endotermica.pdf
Modelagem de um CSTR com reação endotermica.pdf
 
Presentation of IEEE Slovenia CIS (Computational Intelligence Society) Chapte...
Presentation of IEEE Slovenia CIS (Computational Intelligence Society) Chapte...Presentation of IEEE Slovenia CIS (Computational Intelligence Society) Chapte...
Presentation of IEEE Slovenia CIS (Computational Intelligence Society) Chapte...
 
ML Based Model for NIDS MSc Updated Presentation.v2.pptx
ML Based Model for NIDS MSc Updated Presentation.v2.pptxML Based Model for NIDS MSc Updated Presentation.v2.pptx
ML Based Model for NIDS MSc Updated Presentation.v2.pptx
 
spirit beverages ppt without graphics.pptx
spirit beverages ppt without graphics.pptxspirit beverages ppt without graphics.pptx
spirit beverages ppt without graphics.pptx
 
Question paper of renewable energy sources
Question paper of renewable energy sourcesQuestion paper of renewable energy sources
Question paper of renewable energy sources
 
学校原版美国波士顿大学毕业证学历学位证书原版一模一样
学校原版美国波士顿大学毕业证学历学位证书原版一模一样学校原版美国波士顿大学毕业证学历学位证书原版一模一样
学校原版美国波士顿大学毕业证学历学位证书原版一模一样
 
basic-wireline-operations-course-mahmoud-f-radwan.pdf
basic-wireline-operations-course-mahmoud-f-radwan.pdfbasic-wireline-operations-course-mahmoud-f-radwan.pdf
basic-wireline-operations-course-mahmoud-f-radwan.pdf
 
22CYT12-Unit-V-E Waste and its Management.ppt
22CYT12-Unit-V-E Waste and its Management.ppt22CYT12-Unit-V-E Waste and its Management.ppt
22CYT12-Unit-V-E Waste and its Management.ppt
 
2008 BUILDING CONSTRUCTION Illustrated - Ching Chapter 02 The Building.pdf
2008 BUILDING CONSTRUCTION Illustrated - Ching Chapter 02 The Building.pdf2008 BUILDING CONSTRUCTION Illustrated - Ching Chapter 02 The Building.pdf
2008 BUILDING CONSTRUCTION Illustrated - Ching Chapter 02 The Building.pdf
 
Engine Lubrication performance System.pdf
Engine Lubrication performance System.pdfEngine Lubrication performance System.pdf
Engine Lubrication performance System.pdf
 
官方认证美国密歇根州立大学毕业证学位证书原版一模一样
官方认证美国密歇根州立大学毕业证学位证书原版一模一样官方认证美国密歇根州立大学毕业证学位证书原版一模一样
官方认证美国密歇根州立大学毕业证学位证书原版一模一样
 
Iron and Steel Technology Roadmap - Towards more sustainable steelmaking.pdf
Iron and Steel Technology Roadmap - Towards more sustainable steelmaking.pdfIron and Steel Technology Roadmap - Towards more sustainable steelmaking.pdf
Iron and Steel Technology Roadmap - Towards more sustainable steelmaking.pdf
 
A review on techniques and modelling methodologies used for checking electrom...
A review on techniques and modelling methodologies used for checking electrom...A review on techniques and modelling methodologies used for checking electrom...
A review on techniques and modelling methodologies used for checking electrom...
 
Advanced control scheme of doubly fed induction generator for wind turbine us...
Advanced control scheme of doubly fed induction generator for wind turbine us...Advanced control scheme of doubly fed induction generator for wind turbine us...
Advanced control scheme of doubly fed induction generator for wind turbine us...
 
Casting-Defect-inSlab continuous casting.pdf
Casting-Defect-inSlab continuous casting.pdfCasting-Defect-inSlab continuous casting.pdf
Casting-Defect-inSlab continuous casting.pdf
 
Engineering Drawings Lecture Detail Drawings 2014.pdf
Engineering Drawings Lecture Detail Drawings 2014.pdfEngineering Drawings Lecture Detail Drawings 2014.pdf
Engineering Drawings Lecture Detail Drawings 2014.pdf
 

Deep Learning and its Applications - Computer Vision

  • 1. The image part with relationship ID rId14 was not found in the file. { Deep  Learning And  Its  Applications:  Computer  Vision Adam  Gibson {  deeplearning4j.org  //  skymind.io  //  zipfian  academy
  • 2. The image part with relationship ID rId14 was not found in the file. •  Object  Recognition •  Image  Categorization •  Scene  Parsing •  Face  Recognition Computer  Vision:  A  Primer
  • 3. The image part with relationship ID rId14 was not found in the file. •  OpenCV   •  SIFT •  Filters/Edge  Detection •  Feature  Extraction What’s  currently  done?
  • 4. The image part with relationship ID rId14 was not found in the file. •  Representation  Learning   •  More  precise  than  hand-­‐‑done   features •  Non-­‐‑linearities  and  higher-­‐‑order   trends •  Pretrain  and  Hessian  Free This  is  manual!
  • 5. The image part with relationship ID rId14 was not found in the file. •  Representation  Learning •  Position  Invariance  with  convolutions •  Semantic  Hashing   Deep  Learning  and  Images
  • 6. The image part with relationship ID rId14 was not found in the file. •  Normal  pixels  –  0-­‐‑255  –   normalization •  Sparse  –  binarization  (depending  on   pixel  presence) Different  kinds  of  images
  • 7. The image part with relationship ID rId14 was not found in the file. •  Faces  =  a  collection  of  images. •  With  persistent  pa_erns  of  pixels. •  Pixel  pa_erns  =  features. •  Nets  learn  to  identify  features  in  data,  to   classify  faces  as  faces  and  label  them:  John  or   Sarah. •  Nets  train  by  reconstructing  faces  from  features   many  times. •  Measuring  their  work  against  a  benchmark. Facial  recognition
  • 8. The image part with relationship ID rId14 was not found in the file. DL4J’s  Facial  Reconstructions
  • 9. The image part with relationship ID rId14 was not found in the file. •  Slices  of  a  feature  space  (Max  pooling) •  Learns  different  portions  for  easily  scalable   and  robust  feature  engineering. Position  Invariance  -­‐‑  Convolutions
  • 10. The image part with relationship ID rId14 was not found in the file. Visual  Example  -­‐‑  Convolutions
  • 11. The image part with relationship ID rId14 was not found in the file. Pen  Strokes
  • 12. The image part with relationship ID rId14 was not found in the file. •  Facebook  uses  facial  recognition  to  make   itself  stickier  and  know  more  about  us. •  Government  agencies  use  it  to  secure   national  borders. •  Video  game  makers  use  it  to  construct  more   realistic  worlds. •  Stores  use  it  to  identify  customers  and  track   behavior. What  are  faces  for?
  • 13. The image part with relationship ID rId14 was not found in the file. •  2  layers  of  neuron-­‐‑like  nodes. •  The  1st  is  the  visible,  or  input,  layer •  The  2nd  is  “hidden.”  It  identifies  features  in  input •  Symmetrically  connected. •  “Restricted”  =  no  visible-­‐‑visible  or  hidden-­‐‑hidden   ties •  All  connections  happen  between  layers. Restricted  Bolgmann   Machines  (RBMs)
  • 14. The image part with relationship ID rId14 was not found in the file. •  A  stack  of  RBMs. •  Each  RBM’s  hidden  layer  à  Next  RBM’s  visible/input   layer.   •  DBNs  learn  more  &  more  complex  features •  Example:   •  1)  Pixels  =  input;   •  2)  H1  learns  an  edge  or  line;   •  3)  H2  learns  a  corner  or  set  of  lines;   •  4)  H3  learns  two  groups  of  lines  forming  an  object   -­‐‑-­‐‑  a  face! •  Final  layer  classifies  feature  groups:  sunset,  elephant,   flower,  John,  Sarah. Deep-­‐‑Belief  Net  (DBN)
  • 15. The image part with relationship ID rId14 was not found in the file. •  2  DBNs. •  1st  DBN  *encodes*  data  into  vector  of  10-­‐‑30   numbers  =  Pre-­‐‑training. •  2nd  DBN  decodes  data  into  original  state. •  Backprop  only  happens  on  2nd  DBN •  2nd  is  the  fine-­‐‑tuning  stage  (reconstruction  entropy). •  Reduces  documents  or  images  to  compact  vectors  . •  Useful  in  search,  QA  and  information  retrieval. Deep  Autoencoder
  • 16. The image part with relationship ID rId14 was not found in the file. Deep  Autoencoder  Architecture
  • 17. The image part with relationship ID rId14 was not found in the file. Image  Search  Results
  • 18. The image part with relationship ID rId14 was not found in the file. •  Top-­‐‑down  &  hierarchical  rather  than  feed-­‐‑forward  (DBNs). •  Handles  sequence-­‐‑based  classification,  windows  of  several   events,  entire  scenes  (multiple  objects). •  Features  themselves  are  vectors.   •  A  tensor  =  a  multi-­‐‑dimensional  matrix,  or  multiple  matrices  of   the  same  size. Recursive  Neural  Tensor  Net
  • 19. The image part with relationship ID rId14 was not found in the file. RNTNs  &  Scene  Composition