SlideShare a Scribd company logo
Goals
 My goal is not to teach you Cognitive Toolkit programming
 I will have some code samples
 But they are illustrative
 CNTK has great Tutorials for that: https://aka.ms/cntk_tut
 I want to get you excited for Deep Learning
 I want you to think about the possibilities
 I want you to understand how far it’s come
 In so short a time
 And what that means for the future
Agenda
 The old “state of the art”
 Deep Learning
 What happened? Why?
 What does Deep Learning enable
 Image Recognition, Transfer Learning
 Object Detection, Image Understanding
 Semantic Segmentation
 Image Generation, Style Transfer, Adversarial Networks
 Issues
 The Future
Evolution vs. Revolution
 Image Processing had been evolving for years
 Chaining complex “convolutions” helped
 However, it was only making incremental improvements
 State-of-the-art custom featurizers
 Could not perform complex image recognition tasks
 Still lacked performance close to humans on simple ones
Convolutional Filters
 Traditional Filter-based methods still work
2012
WINTER
2012
SUMMER
CAT FACES, 12 people, news articles…
FUEL + SPARK + ENGINE
COMPUTER
HORSEPOWER
+
NEW
MATH+MASSIVE
DATA
Massive Data
 Iris dataset: 150 instances, 4 classes
 ImageNet dataset: 1.2M instances, 1000 classes
 Facebook (as of four years ago): 3.5M images / day
 That’s pre-Snapchat!
1965
1975
1995
1985 5,000,000
2005
160,000,000
2015
7,600,000,000
( 2010 )
1,000,000,000
Deep Learning
 Shallow networks
 Deep networks (Inception v3 – ResNet152 wouldn’t fit)
Deep Neural Networks
 Deeper Networks
 Represent large non-linear function
 Easy to train by “pushing” weights in the
right direction
 “Smarter” Neurons
 CNNs learn those complex convolution filters
“automagically”
 RNNs learn to pay attention to the right bits
of history
Recognition Error – Shallow vs. Deep
shallow shallow
AlexNet, 8 layers 8 layers
GoogLeNet, 22 layers
(VGG @ 19/7.3)
ResNet152, 152 layers
0
20
40
60
80
100
120
140
160
2010 2011 2012 2013 2014 2015
layers error
* Feature visualization images from “Visualizing and Understanding Convolutional Neural Networks”, Zeiler and Fergus, ECCV 2014.
… in CNTK
def create_basic_model(input, out_dims):
with C.layers.default_options(init=C.glorot_uniform(), activation=C.relu):
net = C.layers.Convolution((5,5), 32, pad=True)(input)
net = C.layers.MaxPooling((3,3), strides=(2,2))(net)
net = C.layers.Convolution((5,5), 32, pad=True)(net)
net = C.layers.MaxPooling((3,3), strides=(2,2))(net)
net = C.layers.Convolution((5,5), 64, pad=True)(net)
net = C.layers.MaxPooling((3,3), strides=(2,2))(net)
net = C.layers.Dense(64)(net)
net = C.layers.Dense(out_dims, activation=None)(net)
What is it?
 DNNs are uncommonly good at learning abstractions
 Trained CNNs can be adapted to alternate domains
 Far less data required
 More data depending on how far the domain is from trained
 Custom Vision Service
…in CNTK
def create_model(model_uri, num_classes, input_features, feature_node_name, last_hidden_name, new_prediction_node_name='pr
base_model = C.load_model(download_from_uri(model_uri))
feature_node = C.logging.find_by_name(base_model, feature_node_name)
last_node = C.logging.find_by_name(base_model, last_hidden_name)
cloned_layers = C.combine([last_node.owner]).clone(C.CloneMethod.clone,
{feature_node: C.placeholder(name='features')})
feat_norm = input_features - C.Constant(114)
cloned_out = cloned_layers(feat_norm)
return C.layers.Dense(num_classes, activation=None, name=new_prediction_node_name) (cloned_out)
Example: Leak Detection
 https://aka.ms/leak_detection
 Convert audio into images
 Use FFT to convert to frequency domain
 Aggregate across time window and frequency into image:
Example: Using Custom Vision Service
 Detecting food using
mobile apps
 https://aka.ms/cvs_food
 “Layered” models to
reduce confusion
Regions of Interest
 Selection of bounding boxes
 Often random sizes and locations
 Major differentiator between methods
 Region Proposal Network (RPN)
 Initially done with separate SVM – super slow!
 Faster: Train class and RPN simultaneously
 YOLO9000
 Lots of tricks to make it fast
Sumo Wrestlers
Highlights
 Per-pixel classification
 Multiple Methods
 Mask-RCNN
 Multitask Network Cascades
 Recurrent Attention Networks
 Most involve simultaneous
training (like in RCNNs
RoIs
Style Transfer of Mona Lisa
How Does It Work?
 Trade off content vs. style
 Loss function
 L(x)=αC(x)+βS(x)+T(x)
 Content weighs more heavily in early layers
 Style weighs more heavily in later layers
 Tutorial on CNTK
…in CNTK
y = C.input_variable((3, SIZE, SIZE), needs_gradient=True)
z, intermediate_layers = model(y, layers)
content_activations = ordered_outputs(intermediate_layers, {y: [[content]]})
style_activations = ordered_outputs(intermediate_layers, {y: [[style]]})
style_output = np.squeeze(z.eval({y: [[style]]}))
total = (1-decay**(n+1))/(1-decay) # makes sure that changing the decay does not affect the magnitude of content/style
loss = (1.0/total * content_weight * content_loss(y, content)
+ 1.0/total * style_weight * style_loss(z, style_output)
+ total_variation_loss(y))
Generative Adversarial Networks
 Two networks
 Generator takes input, generates images
 Discriminator takes images, determines if fake
 Train both at same time – generator learns to fool discriminator
… in CNTK
def convolutional_generator(z):
…
h2 = C.layers.ConvolutionTranspose2D(gkernel,
num_filters=gf_dim*2,
strides=gstride,
pad=True,
output_shape=(s_h2, s_w2),
activation=None)(h1)
…
return C.reshape(h3, img_h * img_w)
Super Resolution GANs
 GANs Up-res
images
 Just shown
small and
large versions
so training
data is easy https://arxiv.org/pdf/1609.04802.pdf
GANs on Steroids
 CycleGANs is currently the best
 GANs fighting GANs
 Changing so fast it has its own zoo
 https://www.youtube.com/watch?v=IbjF5VjniVE
 Yann LeCun says
 “The most important idea in ML in the last 10 years”
How fast are GANs changing?
Credit: Bruno Gavranović
CycleGAN Results
Neural Networks Can Be Fooled
 https://blog.openai.com/adversarial-example-research/
 Networks are learning a large non-linear equation
 “Intelligent” noise finds “alternate” solution
Regulations, Liability, Social Issues
 NNs doing medical diagnoses
 How do you regulate? If it’s wrong, where does the fault lie?
 Garbage in, garbage out
 FaceApp “Whitewashing”
 Economic Displacement
 Job losses
 Privacy
 Better, faster facial recognition, voiceprinting
 #FakeNews
 Autogeneration of fake audio, video
Deep Learning Toolkits
 CNTK
 1-bit SGD for better distributed training
 TensorFlow
 Momentum
 Chainer
 Torch
 Caffe
 MXNet
 Azure Linux and Windows GPU VMs
What Does the Future Hold?
 Adversaries
 Adversarial networks
 Adversarial examples
 Reinforcement
 Deep RL
 “Training” DL
 Mixture of Networks
 RNNs + CNNs
 Conv + Deconv
Call to action
 CNTK Tutorials
 In GitHub: https://aka.ms/cntk_tut
 On Notebooks.azure.com/cntk
 Finding the latest papers
 arXiv (https://arxiv.org/) …
 And even more important arXiv Sanity Preserver: http://www.arxiv-
sanity.com/
 Re-visit de:code session recordings on Channel 9.
 Continue your education at
Microsoft Virtual Academy online.
[AI07] Revolutionizing Image Processing with Cognitive Toolkit

More Related Content

What's hot

Introduction to Chainer 11 may,2018
Introduction to Chainer 11 may,2018Introduction to Chainer 11 may,2018
Introduction to Chainer 11 may,2018Preferred Networks
 
Metta Innovations - Introdução ao Deep Learning aplicado a vídeo analytics
Metta Innovations - Introdução ao Deep Learning aplicado a vídeo analyticsMetta Innovations - Introdução ao Deep Learning aplicado a vídeo analytics
Metta Innovations - Introdução ao Deep Learning aplicado a vídeo analyticsEduardo Gaspar
 
Deep Learning with TensorFlow: Understanding Tensors, Computations Graphs, Im...
Deep Learning with TensorFlow: Understanding Tensors, Computations Graphs, Im...Deep Learning with TensorFlow: Understanding Tensors, Computations Graphs, Im...
Deep Learning with TensorFlow: Understanding Tensors, Computations Graphs, Im...Altoros
 
Chainer OpenPOWER developer congress HandsON 20170522_ota
Chainer OpenPOWER developer congress HandsON 20170522_otaChainer OpenPOWER developer congress HandsON 20170522_ota
Chainer OpenPOWER developer congress HandsON 20170522_otaPreferred Networks
 
AWS re:Invent 2016: Using MXNet for Recommendation Modeling at Scale (MAC306)
AWS re:Invent 2016: Using MXNet for Recommendation Modeling at Scale (MAC306)AWS re:Invent 2016: Using MXNet for Recommendation Modeling at Scale (MAC306)
AWS re:Invent 2016: Using MXNet for Recommendation Modeling at Scale (MAC306)Amazon Web Services
 
Introduction to Chainer
Introduction to ChainerIntroduction to Chainer
Introduction to ChainerShunta Saito
 
Intro to the Distributed Version of TensorFlow
Intro to the Distributed Version of TensorFlowIntro to the Distributed Version of TensorFlow
Intro to the Distributed Version of TensorFlowAltoros
 
Anomaly Detection at Scale
Anomaly Detection at ScaleAnomaly Detection at Scale
Anomaly Detection at ScaleJeff Henrikson
 
Basic ideas on keras framework
Basic ideas on keras frameworkBasic ideas on keras framework
Basic ideas on keras frameworkAlison Marczewski
 
Keras: Deep Learning Library for Python
Keras: Deep Learning Library for PythonKeras: Deep Learning Library for Python
Keras: Deep Learning Library for PythonRafi Khan
 
Mastering Computer Vision Problems with State-of-the-art Deep Learning
Mastering Computer Vision Problems with State-of-the-art Deep LearningMastering Computer Vision Problems with State-of-the-art Deep Learning
Mastering Computer Vision Problems with State-of-the-art Deep LearningMiguel González-Fierro
 
Caffe framework tutorial2
Caffe framework tutorial2Caffe framework tutorial2
Caffe framework tutorial2Park Chunduck
 
CUDA and Caffe for deep learning
CUDA and Caffe for deep learningCUDA and Caffe for deep learning
CUDA and Caffe for deep learningAmgad Muhammad
 
TensorFlow and Keras: An Overview
TensorFlow and Keras: An OverviewTensorFlow and Keras: An Overview
TensorFlow and Keras: An OverviewPoo Kuan Hoong
 
Applying your Convolutional Neural Networks
Applying your Convolutional Neural NetworksApplying your Convolutional Neural Networks
Applying your Convolutional Neural NetworksDatabricks
 
Deep Learning with Microsoft R Open
Deep Learning with Microsoft R OpenDeep Learning with Microsoft R Open
Deep Learning with Microsoft R OpenPoo Kuan Hoong
 
An Introduction to TensorFlow architecture
An Introduction to TensorFlow architectureAn Introduction to TensorFlow architecture
An Introduction to TensorFlow architectureMani Goswami
 

What's hot (20)

Introduction to Chainer 11 may,2018
Introduction to Chainer 11 may,2018Introduction to Chainer 11 may,2018
Introduction to Chainer 11 may,2018
 
Metta Innovations - Introdução ao Deep Learning aplicado a vídeo analytics
Metta Innovations - Introdução ao Deep Learning aplicado a vídeo analyticsMetta Innovations - Introdução ao Deep Learning aplicado a vídeo analytics
Metta Innovations - Introdução ao Deep Learning aplicado a vídeo analytics
 
Deep Learning with TensorFlow: Understanding Tensors, Computations Graphs, Im...
Deep Learning with TensorFlow: Understanding Tensors, Computations Graphs, Im...Deep Learning with TensorFlow: Understanding Tensors, Computations Graphs, Im...
Deep Learning with TensorFlow: Understanding Tensors, Computations Graphs, Im...
 
Chainer OpenPOWER developer congress HandsON 20170522_ota
Chainer OpenPOWER developer congress HandsON 20170522_otaChainer OpenPOWER developer congress HandsON 20170522_ota
Chainer OpenPOWER developer congress HandsON 20170522_ota
 
ChainerX and How to Take Part
ChainerX and How to Take PartChainerX and How to Take Part
ChainerX and How to Take Part
 
AWS re:Invent 2016: Using MXNet for Recommendation Modeling at Scale (MAC306)
AWS re:Invent 2016: Using MXNet for Recommendation Modeling at Scale (MAC306)AWS re:Invent 2016: Using MXNet for Recommendation Modeling at Scale (MAC306)
AWS re:Invent 2016: Using MXNet for Recommendation Modeling at Scale (MAC306)
 
Introduction to Chainer
Introduction to ChainerIntroduction to Chainer
Introduction to Chainer
 
Intro to the Distributed Version of TensorFlow
Intro to the Distributed Version of TensorFlowIntro to the Distributed Version of TensorFlow
Intro to the Distributed Version of TensorFlow
 
Anomaly Detection at Scale
Anomaly Detection at ScaleAnomaly Detection at Scale
Anomaly Detection at Scale
 
Basic ideas on keras framework
Basic ideas on keras frameworkBasic ideas on keras framework
Basic ideas on keras framework
 
Keras: Deep Learning Library for Python
Keras: Deep Learning Library for PythonKeras: Deep Learning Library for Python
Keras: Deep Learning Library for Python
 
Mastering Computer Vision Problems with State-of-the-art Deep Learning
Mastering Computer Vision Problems with State-of-the-art Deep LearningMastering Computer Vision Problems with State-of-the-art Deep Learning
Mastering Computer Vision Problems with State-of-the-art Deep Learning
 
Caffe framework tutorial2
Caffe framework tutorial2Caffe framework tutorial2
Caffe framework tutorial2
 
Chainer v4 and v5
Chainer v4 and v5Chainer v4 and v5
Chainer v4 and v5
 
CUDA and Caffe for deep learning
CUDA and Caffe for deep learningCUDA and Caffe for deep learning
CUDA and Caffe for deep learning
 
TensorFlow and Keras: An Overview
TensorFlow and Keras: An OverviewTensorFlow and Keras: An Overview
TensorFlow and Keras: An Overview
 
Applying your Convolutional Neural Networks
Applying your Convolutional Neural NetworksApplying your Convolutional Neural Networks
Applying your Convolutional Neural Networks
 
Deep Learning with Microsoft R Open
Deep Learning with Microsoft R OpenDeep Learning with Microsoft R Open
Deep Learning with Microsoft R Open
 
Pitch v2.2
Pitch v2.2Pitch v2.2
Pitch v2.2
 
An Introduction to TensorFlow architecture
An Introduction to TensorFlow architectureAn Introduction to TensorFlow architecture
An Introduction to TensorFlow architecture
 

Viewers also liked

Caffe - A deep learning framework (Ramin Fahimi)
Caffe - A deep learning framework (Ramin Fahimi)Caffe - A deep learning framework (Ramin Fahimi)
Caffe - A deep learning framework (Ramin Fahimi)irpycon
 
Center loss for Face Recognition
Center loss for Face RecognitionCenter loss for Face Recognition
Center loss for Face RecognitionJisung Kim
 
Computer vision, machine, and deep learning
Computer vision, machine, and deep learningComputer vision, machine, and deep learning
Computer vision, machine, and deep learningIgi Ardiyanto
 
Caffe framework tutorial
Caffe framework tutorialCaffe framework tutorial
Caffe framework tutorialPark Chunduck
 
Optimization in deep learning
Optimization in deep learningOptimization in deep learning
Optimization in deep learningJeremy Nixon
 
Face Recognition Based on Deep Learning (Yurii Pashchenko Technology Stream)
Face Recognition Based on Deep Learning (Yurii Pashchenko Technology Stream) Face Recognition Based on Deep Learning (Yurii Pashchenko Technology Stream)
Face Recognition Based on Deep Learning (Yurii Pashchenko Technology Stream) IT Arena
 
Using Gradient Descent for Optimization and Learning
Using Gradient Descent for Optimization and LearningUsing Gradient Descent for Optimization and Learning
Using Gradient Descent for Optimization and LearningDr. Volkan OBAN
 
DIY Deep Learning with Caffe Workshop
DIY Deep Learning with Caffe WorkshopDIY Deep Learning with Caffe Workshop
DIY Deep Learning with Caffe Workshopodsc
 
Muzammil Abdulrahman PPT On Gabor Wavelet Transform (GWT) Based Facial Expres...
Muzammil Abdulrahman PPT On Gabor Wavelet Transform (GWT) Based Facial Expres...Muzammil Abdulrahman PPT On Gabor Wavelet Transform (GWT) Based Facial Expres...
Muzammil Abdulrahman PPT On Gabor Wavelet Transform (GWT) Based Facial Expres...Petroleum Training Institute
 
Pattern Recognition and Machine Learning : Graphical Models
Pattern Recognition and Machine Learning : Graphical ModelsPattern Recognition and Machine Learning : Graphical Models
Pattern Recognition and Machine Learning : Graphical Modelsbutest
 
Structure Learning of Bayesian Networks with p Nodes from n Samples when n&lt...
Structure Learning of Bayesian Networks with p Nodes from n Samples when n&lt...Structure Learning of Bayesian Networks with p Nodes from n Samples when n&lt...
Structure Learning of Bayesian Networks with p Nodes from n Samples when n&lt...Joe Suzuki
 
Semi fragile watermarking
Semi fragile watermarkingSemi fragile watermarking
Semi fragile watermarkingYash Diwakar
 
Face recognition and deep learning โดย ดร. สรรพฤทธิ์ มฤคทัต NECTEC
Face recognition and deep learning  โดย ดร. สรรพฤทธิ์ มฤคทัต NECTECFace recognition and deep learning  โดย ดร. สรรพฤทธิ์ มฤคทัต NECTEC
Face recognition and deep learning โดย ดร. สรรพฤทธิ์ มฤคทัต NECTECBAINIDA
 
Processor, Compiler and Python Programming Language
Processor, Compiler and Python Programming LanguageProcessor, Compiler and Python Programming Language
Processor, Compiler and Python Programming Languagearumdapta98
 
Rattani - Ph.D. Defense Slides
Rattani - Ph.D. Defense SlidesRattani - Ph.D. Defense Slides
Rattani - Ph.D. Defense SlidesPluribus One
 
Pattern Recognition and Machine Learning: Section 3.3
Pattern Recognition and Machine Learning: Section 3.3Pattern Recognition and Machine Learning: Section 3.3
Pattern Recognition and Machine Learning: Section 3.3Yusuke Oda
 
怖くない誤差逆伝播法 Chainerを添えて
怖くない誤差逆伝播法 Chainerを添えて怖くない誤差逆伝播法 Chainerを添えて
怖くない誤差逆伝播法 Chainerを添えてmarujirou
 

Viewers also liked (20)

портфоліо Бабич О.А.
портфоліо Бабич О.А.портфоліо Бабич О.А.
портфоліо Бабич О.А.
 
Caffe - A deep learning framework (Ramin Fahimi)
Caffe - A deep learning framework (Ramin Fahimi)Caffe - A deep learning framework (Ramin Fahimi)
Caffe - A deep learning framework (Ramin Fahimi)
 
Center loss for Face Recognition
Center loss for Face RecognitionCenter loss for Face Recognition
Center loss for Face Recognition
 
Computer vision, machine, and deep learning
Computer vision, machine, and deep learningComputer vision, machine, and deep learning
Computer vision, machine, and deep learning
 
Caffe framework tutorial
Caffe framework tutorialCaffe framework tutorial
Caffe framework tutorial
 
Facebook Deep face
Facebook Deep faceFacebook Deep face
Facebook Deep face
 
Optimization in deep learning
Optimization in deep learningOptimization in deep learning
Optimization in deep learning
 
Face Recognition Based on Deep Learning (Yurii Pashchenko Technology Stream)
Face Recognition Based on Deep Learning (Yurii Pashchenko Technology Stream) Face Recognition Based on Deep Learning (Yurii Pashchenko Technology Stream)
Face Recognition Based on Deep Learning (Yurii Pashchenko Technology Stream)
 
Using Gradient Descent for Optimization and Learning
Using Gradient Descent for Optimization and LearningUsing Gradient Descent for Optimization and Learning
Using Gradient Descent for Optimization and Learning
 
DIY Deep Learning with Caffe Workshop
DIY Deep Learning with Caffe WorkshopDIY Deep Learning with Caffe Workshop
DIY Deep Learning with Caffe Workshop
 
Muzammil Abdulrahman PPT On Gabor Wavelet Transform (GWT) Based Facial Expres...
Muzammil Abdulrahman PPT On Gabor Wavelet Transform (GWT) Based Facial Expres...Muzammil Abdulrahman PPT On Gabor Wavelet Transform (GWT) Based Facial Expres...
Muzammil Abdulrahman PPT On Gabor Wavelet Transform (GWT) Based Facial Expres...
 
Pattern Recognition and Machine Learning : Graphical Models
Pattern Recognition and Machine Learning : Graphical ModelsPattern Recognition and Machine Learning : Graphical Models
Pattern Recognition and Machine Learning : Graphical Models
 
Structure Learning of Bayesian Networks with p Nodes from n Samples when n&lt...
Structure Learning of Bayesian Networks with p Nodes from n Samples when n&lt...Structure Learning of Bayesian Networks with p Nodes from n Samples when n&lt...
Structure Learning of Bayesian Networks with p Nodes from n Samples when n&lt...
 
Semi fragile watermarking
Semi fragile watermarkingSemi fragile watermarking
Semi fragile watermarking
 
Face recognition and deep learning โดย ดร. สรรพฤทธิ์ มฤคทัต NECTEC
Face recognition and deep learning  โดย ดร. สรรพฤทธิ์ มฤคทัต NECTECFace recognition and deep learning  โดย ดร. สรรพฤทธิ์ มฤคทัต NECTEC
Face recognition and deep learning โดย ดร. สรรพฤทธิ์ มฤคทัต NECTEC
 
Processor, Compiler and Python Programming Language
Processor, Compiler and Python Programming LanguageProcessor, Compiler and Python Programming Language
Processor, Compiler and Python Programming Language
 
Rattani - Ph.D. Defense Slides
Rattani - Ph.D. Defense SlidesRattani - Ph.D. Defense Slides
Rattani - Ph.D. Defense Slides
 
Pattern Recognition and Machine Learning: Section 3.3
Pattern Recognition and Machine Learning: Section 3.3Pattern Recognition and Machine Learning: Section 3.3
Pattern Recognition and Machine Learning: Section 3.3
 
怖くない誤差逆伝播法 Chainerを添えて
怖くない誤差逆伝播法 Chainerを添えて怖くない誤差逆伝播法 Chainerを添えて
怖くない誤差逆伝播法 Chainerを添えて
 
Deep Learning for Computer Vision: Face Recognition (UPC 2016)
Deep Learning for Computer Vision: Face Recognition (UPC 2016)Deep Learning for Computer Vision: Face Recognition (UPC 2016)
Deep Learning for Computer Vision: Face Recognition (UPC 2016)
 

Similar to [AI07] Revolutionizing Image Processing with Cognitive Toolkit

Generative modeling with Convolutional Neural Networks
Generative modeling with Convolutional Neural NetworksGenerative modeling with Convolutional Neural Networks
Generative modeling with Convolutional Neural NetworksDenis Dus
 
Learning Predictive Modeling with TSA and Kaggle
Learning Predictive Modeling with TSA and KaggleLearning Predictive Modeling with TSA and Kaggle
Learning Predictive Modeling with TSA and KaggleYvonne K. Matos
 
Introduction to Deep Learning and Tensorflow
Introduction to Deep Learning and TensorflowIntroduction to Deep Learning and Tensorflow
Introduction to Deep Learning and TensorflowOswald Campesato
 
Diving into Deep Learning (Silicon Valley Code Camp 2017)
Diving into Deep Learning (Silicon Valley Code Camp 2017)Diving into Deep Learning (Silicon Valley Code Camp 2017)
Diving into Deep Learning (Silicon Valley Code Camp 2017)Oswald Campesato
 
Learn to Build an App to Find Similar Images using Deep Learning- Piotr Teterwak
Learn to Build an App to Find Similar Images using Deep Learning- Piotr TeterwakLearn to Build an App to Find Similar Images using Deep Learning- Piotr Teterwak
Learn to Build an App to Find Similar Images using Deep Learning- Piotr TeterwakPyData
 
Week2- Deep Learning Intuition.pptx
Week2- Deep Learning Intuition.pptxWeek2- Deep Learning Intuition.pptx
Week2- Deep Learning Intuition.pptxfahmi324663
 
Accelerating HPC Applications on NVIDIA GPUs with OpenACC
Accelerating HPC Applications on NVIDIA GPUs with OpenACCAccelerating HPC Applications on NVIDIA GPUs with OpenACC
Accelerating HPC Applications on NVIDIA GPUs with OpenACCinside-BigData.com
 
Deep Dive on Deep Learning (June 2018)
Deep Dive on Deep Learning (June 2018)Deep Dive on Deep Learning (June 2018)
Deep Dive on Deep Learning (June 2018)Julien SIMON
 
Camp IT: Making the World More Efficient Using AI & Machine Learning
Camp IT: Making the World More Efficient Using AI & Machine LearningCamp IT: Making the World More Efficient Using AI & Machine Learning
Camp IT: Making the World More Efficient Using AI & Machine LearningKrzysztof Kowalczyk
 
Neural network image recognition
Neural network image recognitionNeural network image recognition
Neural network image recognitionOleksii Sekundant
 
Introduction to Deep Learning
Introduction to Deep LearningIntroduction to Deep Learning
Introduction to Deep LearningOswald Campesato
 
Deep Learning And Business Models (VNITC 2015-09-13)
Deep Learning And Business Models (VNITC 2015-09-13)Deep Learning And Business Models (VNITC 2015-09-13)
Deep Learning And Business Models (VNITC 2015-09-13)Ha Phuong
 
Generation of Deepfake images using GAN and Least squares GAN.ppt
Generation of Deepfake images using GAN and Least squares GAN.pptGeneration of Deepfake images using GAN and Least squares GAN.ppt
Generation of Deepfake images using GAN and Least squares GAN.pptDivyaGugulothu
 
AIML4 CNN lab256 1hr (111-1).pdf
AIML4 CNN lab256 1hr (111-1).pdfAIML4 CNN lab256 1hr (111-1).pdf
AIML4 CNN lab256 1hr (111-1).pdfssuserb4d806
 
Introduction to Applied Machine Learning
Introduction to Applied Machine LearningIntroduction to Applied Machine Learning
Introduction to Applied Machine LearningSheilaJimenezMorejon
 
nlp dl 1.pdf
nlp dl 1.pdfnlp dl 1.pdf
nlp dl 1.pdfnyomans1
 
Image De-Noising Using Deep Neural Network
Image De-Noising Using Deep Neural NetworkImage De-Noising Using Deep Neural Network
Image De-Noising Using Deep Neural Networkaciijournal
 
Tutorial: Image Generation and Image-to-Image Translation using GAN
Tutorial: Image Generation and Image-to-Image Translation using GANTutorial: Image Generation and Image-to-Image Translation using GAN
Tutorial: Image Generation and Image-to-Image Translation using GANWuhyun Rico Shin
 

Similar to [AI07] Revolutionizing Image Processing with Cognitive Toolkit (20)

Generative modeling with Convolutional Neural Networks
Generative modeling with Convolutional Neural NetworksGenerative modeling with Convolutional Neural Networks
Generative modeling with Convolutional Neural Networks
 
Learning Predictive Modeling with TSA and Kaggle
Learning Predictive Modeling with TSA and KaggleLearning Predictive Modeling with TSA and Kaggle
Learning Predictive Modeling with TSA and Kaggle
 
Introduction to Deep Learning and Tensorflow
Introduction to Deep Learning and TensorflowIntroduction to Deep Learning and Tensorflow
Introduction to Deep Learning and Tensorflow
 
Android and Deep Learning
Android and Deep LearningAndroid and Deep Learning
Android and Deep Learning
 
Diving into Deep Learning (Silicon Valley Code Camp 2017)
Diving into Deep Learning (Silicon Valley Code Camp 2017)Diving into Deep Learning (Silicon Valley Code Camp 2017)
Diving into Deep Learning (Silicon Valley Code Camp 2017)
 
Learn to Build an App to Find Similar Images using Deep Learning- Piotr Teterwak
Learn to Build an App to Find Similar Images using Deep Learning- Piotr TeterwakLearn to Build an App to Find Similar Images using Deep Learning- Piotr Teterwak
Learn to Build an App to Find Similar Images using Deep Learning- Piotr Teterwak
 
Week2- Deep Learning Intuition.pptx
Week2- Deep Learning Intuition.pptxWeek2- Deep Learning Intuition.pptx
Week2- Deep Learning Intuition.pptx
 
Accelerating HPC Applications on NVIDIA GPUs with OpenACC
Accelerating HPC Applications on NVIDIA GPUs with OpenACCAccelerating HPC Applications on NVIDIA GPUs with OpenACC
Accelerating HPC Applications on NVIDIA GPUs with OpenACC
 
Deep Dive on Deep Learning (June 2018)
Deep Dive on Deep Learning (June 2018)Deep Dive on Deep Learning (June 2018)
Deep Dive on Deep Learning (June 2018)
 
Camp IT: Making the World More Efficient Using AI & Machine Learning
Camp IT: Making the World More Efficient Using AI & Machine LearningCamp IT: Making the World More Efficient Using AI & Machine Learning
Camp IT: Making the World More Efficient Using AI & Machine Learning
 
Neural network image recognition
Neural network image recognitionNeural network image recognition
Neural network image recognition
 
Introduction to Deep Learning
Introduction to Deep LearningIntroduction to Deep Learning
Introduction to Deep Learning
 
Deep Learning And Business Models (VNITC 2015-09-13)
Deep Learning And Business Models (VNITC 2015-09-13)Deep Learning And Business Models (VNITC 2015-09-13)
Deep Learning And Business Models (VNITC 2015-09-13)
 
Generation of Deepfake images using GAN and Least squares GAN.ppt
Generation of Deepfake images using GAN and Least squares GAN.pptGeneration of Deepfake images using GAN and Least squares GAN.ppt
Generation of Deepfake images using GAN and Least squares GAN.ppt
 
AIML4 CNN lab256 1hr (111-1).pdf
AIML4 CNN lab256 1hr (111-1).pdfAIML4 CNN lab256 1hr (111-1).pdf
AIML4 CNN lab256 1hr (111-1).pdf
 
Introduction to Applied Machine Learning
Introduction to Applied Machine LearningIntroduction to Applied Machine Learning
Introduction to Applied Machine Learning
 
nlp dl 1.pdf
nlp dl 1.pdfnlp dl 1.pdf
nlp dl 1.pdf
 
Eye deep
Eye deepEye deep
Eye deep
 
Image De-Noising Using Deep Neural Network
Image De-Noising Using Deep Neural NetworkImage De-Noising Using Deep Neural Network
Image De-Noising Using Deep Neural Network
 
Tutorial: Image Generation and Image-to-Image Translation using GAN
Tutorial: Image Generation and Image-to-Image Translation using GANTutorial: Image Generation and Image-to-Image Translation using GAN
Tutorial: Image Generation and Image-to-Image Translation using GAN
 

More from de:code 2017

[AI08] 深層学習フレームワーク Chainer × Microsoft で広がる応用
[AI08] 深層学習フレームワーク Chainer × Microsoft で広がる応用[AI08] 深層学習フレームワーク Chainer × Microsoft で広がる応用
[AI08] 深層学習フレームワーク Chainer × Microsoft で広がる応用de:code 2017
 
[AI10] ゲームキャラクターのための人工知能と社会への応用 ~ FINAL FANTASY XV を事例として ~
[AI10] ゲームキャラクターのための人工知能と社会への応用 ~ FINAL FANTASY XV を事例として ~[AI10] ゲームキャラクターのための人工知能と社会への応用 ~ FINAL FANTASY XV を事例として ~
[AI10] ゲームキャラクターのための人工知能と社会への応用 ~ FINAL FANTASY XV を事例として ~de:code 2017
 
[DO07] マイクロサービスに必要な技術要素はすべて Spring Cloud にある
[DO07] マイクロサービスに必要な技術要素はすべて Spring Cloud にある[DO07] マイクロサービスに必要な技術要素はすべて Spring Cloud にある
[DO07] マイクロサービスに必要な技術要素はすべて Spring Cloud にあるde:code 2017
 
[SC09] パッチ待ちはもう古い!Windows 10 最新セキュリティ技術とゼロデイ攻撃攻防の実例
[SC09] パッチ待ちはもう古い!Windows 10 最新セキュリティ技術とゼロデイ攻撃攻防の実例[SC09] パッチ待ちはもう古い!Windows 10 最新セキュリティ技術とゼロデイ攻撃攻防の実例
[SC09] パッチ待ちはもう古い!Windows 10 最新セキュリティ技術とゼロデイ攻撃攻防の実例de:code 2017
 
[SC10] 自社開発モバイルアプリの DLP 対応化を Microsoft Intune で可能に
[SC10] 自社開発モバイルアプリの DLP 対応化を Microsoft Intune で可能に[SC10] 自社開発モバイルアプリの DLP 対応化を Microsoft Intune で可能に
[SC10] 自社開発モバイルアプリの DLP 対応化を Microsoft Intune で可能にde:code 2017
 
[DI12] あらゆるデータをビジネスに活用! Azure Data Lake を中心としたビックデータ処理基盤のアーキテクチャと実装
[DI12] あらゆるデータをビジネスに活用! Azure Data Lake を中心としたビックデータ処理基盤のアーキテクチャと実装[DI12] あらゆるデータをビジネスに活用! Azure Data Lake を中心としたビックデータ処理基盤のアーキテクチャと実装
[DI12] あらゆるデータをビジネスに活用! Azure Data Lake を中心としたビックデータ処理基盤のアーキテクチャと実装de:code 2017
 
[DI10] IoT を実践する最新のプラクティス ~ Azure IoT Hub 、SDK 、Azure IoT Suite ~
[DI10] IoT を実践する最新のプラクティス ~ Azure IoT Hub 、SDK 、Azure IoT Suite ~[DI10] IoT を実践する最新のプラクティス ~ Azure IoT Hub 、SDK 、Azure IoT Suite ~
[DI10] IoT を実践する最新のプラクティス ~ Azure IoT Hub 、SDK 、Azure IoT Suite ~de:code 2017
 
[AI03] AI × 導入の速さを武器に。 ” 人工知能パーツ ” Cognitive Services の使いどころ
[AI03] AI × 導入の速さを武器に。 ” 人工知能パーツ ” Cognitive Services の使いどころ[AI03] AI × 導入の速さを武器に。 ” 人工知能パーツ ” Cognitive Services の使いどころ
[AI03] AI × 導入の速さを武器に。 ” 人工知能パーツ ” Cognitive Services の使いどころde:code 2017
 
[SP04] これからのエンジニアに必要な「マネジメント」の考え方
[SP04] これからのエンジニアに必要な「マネジメント」の考え方[SP04] これからのエンジニアに必要な「マネジメント」の考え方
[SP04] これからのエンジニアに必要な「マネジメント」の考え方de:code 2017
 
[DO17] セゾン情報システムズの CTO 小野氏による、伝統的 Sier におけるモダン開発への挑戦
[DO17] セゾン情報システムズの CTO 小野氏による、伝統的 Sier におけるモダン開発への挑戦[DO17] セゾン情報システムズの CTO 小野氏による、伝統的 Sier におけるモダン開発への挑戦
[DO17] セゾン情報システムズの CTO 小野氏による、伝統的 Sier におけるモダン開発への挑戦de:code 2017
 
[DO13] 楽天のクラウドストレージ使いこなし術 Azure と OSS で少しずつ進めるレガシー脱却
[DO13] 楽天のクラウドストレージ使いこなし術 Azure と OSS で少しずつ進めるレガシー脱却[DO13] 楽天のクラウドストレージ使いこなし術 Azure と OSS で少しずつ進めるレガシー脱却
[DO13] 楽天のクラウドストレージ使いこなし術 Azure と OSS で少しずつ進めるレガシー脱却de:code 2017
 
[DO11] JOY, Inc. : あなたの仕事場での喜びは何ですか?
[DO11] JOY, Inc. : あなたの仕事場での喜びは何ですか?[DO11] JOY, Inc. : あなたの仕事場での喜びは何ですか?
[DO11] JOY, Inc. : あなたの仕事場での喜びは何ですか?de:code 2017
 
[DO08] 『変わらない開発現場』を変えていくために ~エンプラ系レガシー SIer のための DevOps 再入門~
[DO08] 『変わらない開発現場』を変えていくために ~エンプラ系レガシー SIer のための DevOps 再入門~[DO08] 『変わらない開発現場』を変えていくために ~エンプラ系レガシー SIer のための DevOps 再入門~
[DO08] 『変わらない開発現場』を変えていくために ~エンプラ系レガシー SIer のための DevOps 再入門~de:code 2017
 
[DO06] Infrastructure as Code でサービスを迅速にローンチし、継続的にインフラを変更しよう
[DO06] Infrastructure as Code でサービスを迅速にローンチし、継続的にインフラを変更しよう[DO06] Infrastructure as Code でサービスを迅速にローンチし、継続的にインフラを変更しよう
[DO06] Infrastructure as Code でサービスを迅速にローンチし、継続的にインフラを変更しようde:code 2017
 
[DO05] システムの信頼性を上げるための新しい考え方 SRE ( Site Reliability Engineering ) in Azure, o...
[DO05] システムの信頼性を上げるための新しい考え方 SRE ( Site Reliability Engineering ) in Azure, o...[DO05] システムの信頼性を上げるための新しい考え方 SRE ( Site Reliability Engineering ) in Azure, o...
[DO05] システムの信頼性を上げるための新しい考え方 SRE ( Site Reliability Engineering ) in Azure, o...de:code 2017
 
[DO04] アジャイル開発サバイバルガイド 〜キミが必ず直面する課題と乗り越え方を伝えよう!〜
[DO04] アジャイル開発サバイバルガイド 〜キミが必ず直面する課題と乗り越え方を伝えよう!〜[DO04] アジャイル開発サバイバルガイド 〜キミが必ず直面する課題と乗り越え方を伝えよう!〜
[DO04] アジャイル開発サバイバルガイド 〜キミが必ず直面する課題と乗り越え方を伝えよう!〜de:code 2017
 
[DO02] Jenkins PipelineとBlue Oceanによる、フルスクラッチからの継続的デリバリ
[DO02] Jenkins PipelineとBlue Oceanによる、フルスクラッチからの継続的デリバリ[DO02] Jenkins PipelineとBlue Oceanによる、フルスクラッチからの継続的デリバリ
[DO02] Jenkins PipelineとBlue Oceanによる、フルスクラッチからの継続的デリバリde:code 2017
 
[SP03] 「怠惰の美徳~言語デザイナーの視点から」
[SP03] 「怠惰の美徳~言語デザイナーの視点から」[SP03] 「怠惰の美徳~言語デザイナーの視点から」
[SP03] 「怠惰の美徳~言語デザイナーの視点から」de:code 2017
 
[SP02] Developing autonomous vehicles with AirSim
[SP02] Developing autonomous vehicles with AirSim[SP02] Developing autonomous vehicles with AirSim
[SP02] Developing autonomous vehicles with AirSimde:code 2017
 
[SP01] CTO が語る! 今注目すべきテクノロジー
[SP01] CTO が語る! 今注目すべきテクノロジー[SP01] CTO が語る! 今注目すべきテクノロジー
[SP01] CTO が語る! 今注目すべきテクノロジーde:code 2017
 

More from de:code 2017 (20)

[AI08] 深層学習フレームワーク Chainer × Microsoft で広がる応用
[AI08] 深層学習フレームワーク Chainer × Microsoft で広がる応用[AI08] 深層学習フレームワーク Chainer × Microsoft で広がる応用
[AI08] 深層学習フレームワーク Chainer × Microsoft で広がる応用
 
[AI10] ゲームキャラクターのための人工知能と社会への応用 ~ FINAL FANTASY XV を事例として ~
[AI10] ゲームキャラクターのための人工知能と社会への応用 ~ FINAL FANTASY XV を事例として ~[AI10] ゲームキャラクターのための人工知能と社会への応用 ~ FINAL FANTASY XV を事例として ~
[AI10] ゲームキャラクターのための人工知能と社会への応用 ~ FINAL FANTASY XV を事例として ~
 
[DO07] マイクロサービスに必要な技術要素はすべて Spring Cloud にある
[DO07] マイクロサービスに必要な技術要素はすべて Spring Cloud にある[DO07] マイクロサービスに必要な技術要素はすべて Spring Cloud にある
[DO07] マイクロサービスに必要な技術要素はすべて Spring Cloud にある
 
[SC09] パッチ待ちはもう古い!Windows 10 最新セキュリティ技術とゼロデイ攻撃攻防の実例
[SC09] パッチ待ちはもう古い!Windows 10 最新セキュリティ技術とゼロデイ攻撃攻防の実例[SC09] パッチ待ちはもう古い!Windows 10 最新セキュリティ技術とゼロデイ攻撃攻防の実例
[SC09] パッチ待ちはもう古い!Windows 10 最新セキュリティ技術とゼロデイ攻撃攻防の実例
 
[SC10] 自社開発モバイルアプリの DLP 対応化を Microsoft Intune で可能に
[SC10] 自社開発モバイルアプリの DLP 対応化を Microsoft Intune で可能に[SC10] 自社開発モバイルアプリの DLP 対応化を Microsoft Intune で可能に
[SC10] 自社開発モバイルアプリの DLP 対応化を Microsoft Intune で可能に
 
[DI12] あらゆるデータをビジネスに活用! Azure Data Lake を中心としたビックデータ処理基盤のアーキテクチャと実装
[DI12] あらゆるデータをビジネスに活用! Azure Data Lake を中心としたビックデータ処理基盤のアーキテクチャと実装[DI12] あらゆるデータをビジネスに活用! Azure Data Lake を中心としたビックデータ処理基盤のアーキテクチャと実装
[DI12] あらゆるデータをビジネスに活用! Azure Data Lake を中心としたビックデータ処理基盤のアーキテクチャと実装
 
[DI10] IoT を実践する最新のプラクティス ~ Azure IoT Hub 、SDK 、Azure IoT Suite ~
[DI10] IoT を実践する最新のプラクティス ~ Azure IoT Hub 、SDK 、Azure IoT Suite ~[DI10] IoT を実践する最新のプラクティス ~ Azure IoT Hub 、SDK 、Azure IoT Suite ~
[DI10] IoT を実践する最新のプラクティス ~ Azure IoT Hub 、SDK 、Azure IoT Suite ~
 
[AI03] AI × 導入の速さを武器に。 ” 人工知能パーツ ” Cognitive Services の使いどころ
[AI03] AI × 導入の速さを武器に。 ” 人工知能パーツ ” Cognitive Services の使いどころ[AI03] AI × 導入の速さを武器に。 ” 人工知能パーツ ” Cognitive Services の使いどころ
[AI03] AI × 導入の速さを武器に。 ” 人工知能パーツ ” Cognitive Services の使いどころ
 
[SP04] これからのエンジニアに必要な「マネジメント」の考え方
[SP04] これからのエンジニアに必要な「マネジメント」の考え方[SP04] これからのエンジニアに必要な「マネジメント」の考え方
[SP04] これからのエンジニアに必要な「マネジメント」の考え方
 
[DO17] セゾン情報システムズの CTO 小野氏による、伝統的 Sier におけるモダン開発への挑戦
[DO17] セゾン情報システムズの CTO 小野氏による、伝統的 Sier におけるモダン開発への挑戦[DO17] セゾン情報システムズの CTO 小野氏による、伝統的 Sier におけるモダン開発への挑戦
[DO17] セゾン情報システムズの CTO 小野氏による、伝統的 Sier におけるモダン開発への挑戦
 
[DO13] 楽天のクラウドストレージ使いこなし術 Azure と OSS で少しずつ進めるレガシー脱却
[DO13] 楽天のクラウドストレージ使いこなし術 Azure と OSS で少しずつ進めるレガシー脱却[DO13] 楽天のクラウドストレージ使いこなし術 Azure と OSS で少しずつ進めるレガシー脱却
[DO13] 楽天のクラウドストレージ使いこなし術 Azure と OSS で少しずつ進めるレガシー脱却
 
[DO11] JOY, Inc. : あなたの仕事場での喜びは何ですか?
[DO11] JOY, Inc. : あなたの仕事場での喜びは何ですか?[DO11] JOY, Inc. : あなたの仕事場での喜びは何ですか?
[DO11] JOY, Inc. : あなたの仕事場での喜びは何ですか?
 
[DO08] 『変わらない開発現場』を変えていくために ~エンプラ系レガシー SIer のための DevOps 再入門~
[DO08] 『変わらない開発現場』を変えていくために ~エンプラ系レガシー SIer のための DevOps 再入門~[DO08] 『変わらない開発現場』を変えていくために ~エンプラ系レガシー SIer のための DevOps 再入門~
[DO08] 『変わらない開発現場』を変えていくために ~エンプラ系レガシー SIer のための DevOps 再入門~
 
[DO06] Infrastructure as Code でサービスを迅速にローンチし、継続的にインフラを変更しよう
[DO06] Infrastructure as Code でサービスを迅速にローンチし、継続的にインフラを変更しよう[DO06] Infrastructure as Code でサービスを迅速にローンチし、継続的にインフラを変更しよう
[DO06] Infrastructure as Code でサービスを迅速にローンチし、継続的にインフラを変更しよう
 
[DO05] システムの信頼性を上げるための新しい考え方 SRE ( Site Reliability Engineering ) in Azure, o...
[DO05] システムの信頼性を上げるための新しい考え方 SRE ( Site Reliability Engineering ) in Azure, o...[DO05] システムの信頼性を上げるための新しい考え方 SRE ( Site Reliability Engineering ) in Azure, o...
[DO05] システムの信頼性を上げるための新しい考え方 SRE ( Site Reliability Engineering ) in Azure, o...
 
[DO04] アジャイル開発サバイバルガイド 〜キミが必ず直面する課題と乗り越え方を伝えよう!〜
[DO04] アジャイル開発サバイバルガイド 〜キミが必ず直面する課題と乗り越え方を伝えよう!〜[DO04] アジャイル開発サバイバルガイド 〜キミが必ず直面する課題と乗り越え方を伝えよう!〜
[DO04] アジャイル開発サバイバルガイド 〜キミが必ず直面する課題と乗り越え方を伝えよう!〜
 
[DO02] Jenkins PipelineとBlue Oceanによる、フルスクラッチからの継続的デリバリ
[DO02] Jenkins PipelineとBlue Oceanによる、フルスクラッチからの継続的デリバリ[DO02] Jenkins PipelineとBlue Oceanによる、フルスクラッチからの継続的デリバリ
[DO02] Jenkins PipelineとBlue Oceanによる、フルスクラッチからの継続的デリバリ
 
[SP03] 「怠惰の美徳~言語デザイナーの視点から」
[SP03] 「怠惰の美徳~言語デザイナーの視点から」[SP03] 「怠惰の美徳~言語デザイナーの視点から」
[SP03] 「怠惰の美徳~言語デザイナーの視点から」
 
[SP02] Developing autonomous vehicles with AirSim
[SP02] Developing autonomous vehicles with AirSim[SP02] Developing autonomous vehicles with AirSim
[SP02] Developing autonomous vehicles with AirSim
 
[SP01] CTO が語る! 今注目すべきテクノロジー
[SP01] CTO が語る! 今注目すべきテクノロジー[SP01] CTO が語る! 今注目すべきテクノロジー
[SP01] CTO が語る! 今注目すべきテクノロジー
 

Recently uploaded

10 Differences between Sales Cloud and CPQ, Blanka Doktorová
10 Differences between Sales Cloud and CPQ, Blanka Doktorová10 Differences between Sales Cloud and CPQ, Blanka Doktorová
10 Differences between Sales Cloud and CPQ, Blanka DoktorováCzechDreamin
 
Search and Society: Reimagining Information Access for Radical Futures
Search and Society: Reimagining Information Access for Radical FuturesSearch and Society: Reimagining Information Access for Radical Futures
Search and Society: Reimagining Information Access for Radical FuturesBhaskar Mitra
 
Kubernetes & AI - Beauty and the Beast !?! @KCD Istanbul 2024
Kubernetes & AI - Beauty and the Beast !?! @KCD Istanbul 2024Kubernetes & AI - Beauty and the Beast !?! @KCD Istanbul 2024
Kubernetes & AI - Beauty and the Beast !?! @KCD Istanbul 2024Tobias Schneck
 
AI revolution and Salesforce, Jiří Karpíšek
AI revolution and Salesforce, Jiří KarpíšekAI revolution and Salesforce, Jiří Karpíšek
AI revolution and Salesforce, Jiří KarpíšekCzechDreamin
 
UiPath Test Automation using UiPath Test Suite series, part 3
UiPath Test Automation using UiPath Test Suite series, part 3UiPath Test Automation using UiPath Test Suite series, part 3
UiPath Test Automation using UiPath Test Suite series, part 3DianaGray10
 
IESVE for Early Stage Design and Planning
IESVE for Early Stage Design and PlanningIESVE for Early Stage Design and Planning
IESVE for Early Stage Design and PlanningIES VE
 
Slack (or Teams) Automation for Bonterra Impact Management (fka Social Soluti...
Slack (or Teams) Automation for Bonterra Impact Management (fka Social Soluti...Slack (or Teams) Automation for Bonterra Impact Management (fka Social Soluti...
Slack (or Teams) Automation for Bonterra Impact Management (fka Social Soluti...Jeffrey Haguewood
 
Future Visions: Predictions to Guide and Time Tech Innovation, Peter Udo Diehl
Future Visions: Predictions to Guide and Time Tech Innovation, Peter Udo DiehlFuture Visions: Predictions to Guide and Time Tech Innovation, Peter Udo Diehl
Future Visions: Predictions to Guide and Time Tech Innovation, Peter Udo DiehlPeter Udo Diehl
 
Knowledge engineering: from people to machines and back
Knowledge engineering: from people to machines and backKnowledge engineering: from people to machines and back
Knowledge engineering: from people to machines and backElena Simperl
 
Custom Approval Process: A New Perspective, Pavel Hrbacek & Anindya Halder
Custom Approval Process: A New Perspective, Pavel Hrbacek & Anindya HalderCustom Approval Process: A New Perspective, Pavel Hrbacek & Anindya Halder
Custom Approval Process: A New Perspective, Pavel Hrbacek & Anindya HalderCzechDreamin
 
Key Trends Shaping the Future of Infrastructure.pdf
Key Trends Shaping the Future of Infrastructure.pdfKey Trends Shaping the Future of Infrastructure.pdf
Key Trends Shaping the Future of Infrastructure.pdfCheryl Hung
 
De-mystifying Zero to One: Design Informed Techniques for Greenfield Innovati...
De-mystifying Zero to One: Design Informed Techniques for Greenfield Innovati...De-mystifying Zero to One: Design Informed Techniques for Greenfield Innovati...
De-mystifying Zero to One: Design Informed Techniques for Greenfield Innovati...Product School
 
AI for Every Business: Unlocking Your Product's Universal Potential by VP of ...
AI for Every Business: Unlocking Your Product's Universal Potential by VP of ...AI for Every Business: Unlocking Your Product's Universal Potential by VP of ...
AI for Every Business: Unlocking Your Product's Universal Potential by VP of ...Product School
 
Introduction to Open Source RAG and RAG Evaluation
Introduction to Open Source RAG and RAG EvaluationIntroduction to Open Source RAG and RAG Evaluation
Introduction to Open Source RAG and RAG EvaluationZilliz
 
Salesforce Adoption – Metrics, Methods, and Motivation, Antone Kom
Salesforce Adoption – Metrics, Methods, and Motivation, Antone KomSalesforce Adoption – Metrics, Methods, and Motivation, Antone Kom
Salesforce Adoption – Metrics, Methods, and Motivation, Antone KomCzechDreamin
 
In-Depth Performance Testing Guide for IT Professionals
In-Depth Performance Testing Guide for IT ProfessionalsIn-Depth Performance Testing Guide for IT Professionals
In-Depth Performance Testing Guide for IT ProfessionalsExpeed Software
 
SOQL 201 for Admins & Developers: Slice & Dice Your Org’s Data With Aggregate...
SOQL 201 for Admins & Developers: Slice & Dice Your Org’s Data With Aggregate...SOQL 201 for Admins & Developers: Slice & Dice Your Org’s Data With Aggregate...
SOQL 201 for Admins & Developers: Slice & Dice Your Org’s Data With Aggregate...CzechDreamin
 
Assuring Contact Center Experiences for Your Customers With ThousandEyes
Assuring Contact Center Experiences for Your Customers With ThousandEyesAssuring Contact Center Experiences for Your Customers With ThousandEyes
Assuring Contact Center Experiences for Your Customers With ThousandEyesThousandEyes
 
Unsubscribed: Combat Subscription Fatigue With a Membership Mentality by Head...
Unsubscribed: Combat Subscription Fatigue With a Membership Mentality by Head...Unsubscribed: Combat Subscription Fatigue With a Membership Mentality by Head...
Unsubscribed: Combat Subscription Fatigue With a Membership Mentality by Head...Product School
 
UiPath Test Automation using UiPath Test Suite series, part 2
UiPath Test Automation using UiPath Test Suite series, part 2UiPath Test Automation using UiPath Test Suite series, part 2
UiPath Test Automation using UiPath Test Suite series, part 2DianaGray10
 

Recently uploaded (20)

10 Differences between Sales Cloud and CPQ, Blanka Doktorová
10 Differences between Sales Cloud and CPQ, Blanka Doktorová10 Differences between Sales Cloud and CPQ, Blanka Doktorová
10 Differences between Sales Cloud and CPQ, Blanka Doktorová
 
Search and Society: Reimagining Information Access for Radical Futures
Search and Society: Reimagining Information Access for Radical FuturesSearch and Society: Reimagining Information Access for Radical Futures
Search and Society: Reimagining Information Access for Radical Futures
 
Kubernetes & AI - Beauty and the Beast !?! @KCD Istanbul 2024
Kubernetes & AI - Beauty and the Beast !?! @KCD Istanbul 2024Kubernetes & AI - Beauty and the Beast !?! @KCD Istanbul 2024
Kubernetes & AI - Beauty and the Beast !?! @KCD Istanbul 2024
 
AI revolution and Salesforce, Jiří Karpíšek
AI revolution and Salesforce, Jiří KarpíšekAI revolution and Salesforce, Jiří Karpíšek
AI revolution and Salesforce, Jiří Karpíšek
 
UiPath Test Automation using UiPath Test Suite series, part 3
UiPath Test Automation using UiPath Test Suite series, part 3UiPath Test Automation using UiPath Test Suite series, part 3
UiPath Test Automation using UiPath Test Suite series, part 3
 
IESVE for Early Stage Design and Planning
IESVE for Early Stage Design and PlanningIESVE for Early Stage Design and Planning
IESVE for Early Stage Design and Planning
 
Slack (or Teams) Automation for Bonterra Impact Management (fka Social Soluti...
Slack (or Teams) Automation for Bonterra Impact Management (fka Social Soluti...Slack (or Teams) Automation for Bonterra Impact Management (fka Social Soluti...
Slack (or Teams) Automation for Bonterra Impact Management (fka Social Soluti...
 
Future Visions: Predictions to Guide and Time Tech Innovation, Peter Udo Diehl
Future Visions: Predictions to Guide and Time Tech Innovation, Peter Udo DiehlFuture Visions: Predictions to Guide and Time Tech Innovation, Peter Udo Diehl
Future Visions: Predictions to Guide and Time Tech Innovation, Peter Udo Diehl
 
Knowledge engineering: from people to machines and back
Knowledge engineering: from people to machines and backKnowledge engineering: from people to machines and back
Knowledge engineering: from people to machines and back
 
Custom Approval Process: A New Perspective, Pavel Hrbacek & Anindya Halder
Custom Approval Process: A New Perspective, Pavel Hrbacek & Anindya HalderCustom Approval Process: A New Perspective, Pavel Hrbacek & Anindya Halder
Custom Approval Process: A New Perspective, Pavel Hrbacek & Anindya Halder
 
Key Trends Shaping the Future of Infrastructure.pdf
Key Trends Shaping the Future of Infrastructure.pdfKey Trends Shaping the Future of Infrastructure.pdf
Key Trends Shaping the Future of Infrastructure.pdf
 
De-mystifying Zero to One: Design Informed Techniques for Greenfield Innovati...
De-mystifying Zero to One: Design Informed Techniques for Greenfield Innovati...De-mystifying Zero to One: Design Informed Techniques for Greenfield Innovati...
De-mystifying Zero to One: Design Informed Techniques for Greenfield Innovati...
 
AI for Every Business: Unlocking Your Product's Universal Potential by VP of ...
AI for Every Business: Unlocking Your Product's Universal Potential by VP of ...AI for Every Business: Unlocking Your Product's Universal Potential by VP of ...
AI for Every Business: Unlocking Your Product's Universal Potential by VP of ...
 
Introduction to Open Source RAG and RAG Evaluation
Introduction to Open Source RAG and RAG EvaluationIntroduction to Open Source RAG and RAG Evaluation
Introduction to Open Source RAG and RAG Evaluation
 
Salesforce Adoption – Metrics, Methods, and Motivation, Antone Kom
Salesforce Adoption – Metrics, Methods, and Motivation, Antone KomSalesforce Adoption – Metrics, Methods, and Motivation, Antone Kom
Salesforce Adoption – Metrics, Methods, and Motivation, Antone Kom
 
In-Depth Performance Testing Guide for IT Professionals
In-Depth Performance Testing Guide for IT ProfessionalsIn-Depth Performance Testing Guide for IT Professionals
In-Depth Performance Testing Guide for IT Professionals
 
SOQL 201 for Admins & Developers: Slice & Dice Your Org’s Data With Aggregate...
SOQL 201 for Admins & Developers: Slice & Dice Your Org’s Data With Aggregate...SOQL 201 for Admins & Developers: Slice & Dice Your Org’s Data With Aggregate...
SOQL 201 for Admins & Developers: Slice & Dice Your Org’s Data With Aggregate...
 
Assuring Contact Center Experiences for Your Customers With ThousandEyes
Assuring Contact Center Experiences for Your Customers With ThousandEyesAssuring Contact Center Experiences for Your Customers With ThousandEyes
Assuring Contact Center Experiences for Your Customers With ThousandEyes
 
Unsubscribed: Combat Subscription Fatigue With a Membership Mentality by Head...
Unsubscribed: Combat Subscription Fatigue With a Membership Mentality by Head...Unsubscribed: Combat Subscription Fatigue With a Membership Mentality by Head...
Unsubscribed: Combat Subscription Fatigue With a Membership Mentality by Head...
 
UiPath Test Automation using UiPath Test Suite series, part 2
UiPath Test Automation using UiPath Test Suite series, part 2UiPath Test Automation using UiPath Test Suite series, part 2
UiPath Test Automation using UiPath Test Suite series, part 2
 

[AI07] Revolutionizing Image Processing with Cognitive Toolkit

  • 1.
  • 2.
  • 3. Goals  My goal is not to teach you Cognitive Toolkit programming  I will have some code samples  But they are illustrative  CNTK has great Tutorials for that: https://aka.ms/cntk_tut  I want to get you excited for Deep Learning  I want you to think about the possibilities  I want you to understand how far it’s come  In so short a time  And what that means for the future
  • 4. Agenda  The old “state of the art”  Deep Learning  What happened? Why?  What does Deep Learning enable  Image Recognition, Transfer Learning  Object Detection, Image Understanding  Semantic Segmentation  Image Generation, Style Transfer, Adversarial Networks  Issues  The Future
  • 5. Evolution vs. Revolution  Image Processing had been evolving for years  Chaining complex “convolutions” helped  However, it was only making incremental improvements  State-of-the-art custom featurizers  Could not perform complex image recognition tasks  Still lacked performance close to humans on simple ones
  • 6. Convolutional Filters  Traditional Filter-based methods still work
  • 7.
  • 10. CAT FACES, 12 people, news articles…
  • 11.
  • 12.
  • 13.
  • 14. FUEL + SPARK + ENGINE COMPUTER HORSEPOWER + NEW MATH+MASSIVE DATA
  • 15. Massive Data  Iris dataset: 150 instances, 4 classes  ImageNet dataset: 1.2M instances, 1000 classes  Facebook (as of four years ago): 3.5M images / day  That’s pre-Snapchat!
  • 18.
  • 19.
  • 20. Deep Learning  Shallow networks  Deep networks (Inception v3 – ResNet152 wouldn’t fit)
  • 21. Deep Neural Networks  Deeper Networks  Represent large non-linear function  Easy to train by “pushing” weights in the right direction  “Smarter” Neurons  CNNs learn those complex convolution filters “automagically”  RNNs learn to pay attention to the right bits of history
  • 22.
  • 23. Recognition Error – Shallow vs. Deep shallow shallow AlexNet, 8 layers 8 layers GoogLeNet, 22 layers (VGG @ 19/7.3) ResNet152, 152 layers 0 20 40 60 80 100 120 140 160 2010 2011 2012 2013 2014 2015 layers error
  • 24.
  • 25. * Feature visualization images from “Visualizing and Understanding Convolutional Neural Networks”, Zeiler and Fergus, ECCV 2014.
  • 26.
  • 27. … in CNTK def create_basic_model(input, out_dims): with C.layers.default_options(init=C.glorot_uniform(), activation=C.relu): net = C.layers.Convolution((5,5), 32, pad=True)(input) net = C.layers.MaxPooling((3,3), strides=(2,2))(net) net = C.layers.Convolution((5,5), 32, pad=True)(net) net = C.layers.MaxPooling((3,3), strides=(2,2))(net) net = C.layers.Convolution((5,5), 64, pad=True)(net) net = C.layers.MaxPooling((3,3), strides=(2,2))(net) net = C.layers.Dense(64)(net) net = C.layers.Dense(out_dims, activation=None)(net)
  • 28.
  • 29.
  • 30. What is it?  DNNs are uncommonly good at learning abstractions  Trained CNNs can be adapted to alternate domains  Far less data required  More data depending on how far the domain is from trained  Custom Vision Service
  • 31. …in CNTK def create_model(model_uri, num_classes, input_features, feature_node_name, last_hidden_name, new_prediction_node_name='pr base_model = C.load_model(download_from_uri(model_uri)) feature_node = C.logging.find_by_name(base_model, feature_node_name) last_node = C.logging.find_by_name(base_model, last_hidden_name) cloned_layers = C.combine([last_node.owner]).clone(C.CloneMethod.clone, {feature_node: C.placeholder(name='features')}) feat_norm = input_features - C.Constant(114) cloned_out = cloned_layers(feat_norm) return C.layers.Dense(num_classes, activation=None, name=new_prediction_node_name) (cloned_out)
  • 32. Example: Leak Detection  https://aka.ms/leak_detection  Convert audio into images  Use FFT to convert to frequency domain  Aggregate across time window and frequency into image:
  • 33. Example: Using Custom Vision Service  Detecting food using mobile apps  https://aka.ms/cvs_food  “Layered” models to reduce confusion
  • 34.
  • 35.
  • 36. Regions of Interest  Selection of bounding boxes  Often random sizes and locations  Major differentiator between methods  Region Proposal Network (RPN)  Initially done with separate SVM – super slow!  Faster: Train class and RPN simultaneously  YOLO9000  Lots of tricks to make it fast
  • 37.
  • 38.
  • 40.
  • 41. Highlights  Per-pixel classification  Multiple Methods  Mask-RCNN  Multitask Network Cascades  Recurrent Attention Networks  Most involve simultaneous training (like in RCNNs RoIs
  • 42.
  • 43.
  • 44. Style Transfer of Mona Lisa
  • 45. How Does It Work?  Trade off content vs. style  Loss function  L(x)=αC(x)+βS(x)+T(x)  Content weighs more heavily in early layers  Style weighs more heavily in later layers  Tutorial on CNTK
  • 46. …in CNTK y = C.input_variable((3, SIZE, SIZE), needs_gradient=True) z, intermediate_layers = model(y, layers) content_activations = ordered_outputs(intermediate_layers, {y: [[content]]}) style_activations = ordered_outputs(intermediate_layers, {y: [[style]]}) style_output = np.squeeze(z.eval({y: [[style]]})) total = (1-decay**(n+1))/(1-decay) # makes sure that changing the decay does not affect the magnitude of content/style loss = (1.0/total * content_weight * content_loss(y, content) + 1.0/total * style_weight * style_loss(z, style_output) + total_variation_loss(y))
  • 47.
  • 48. Generative Adversarial Networks  Two networks  Generator takes input, generates images  Discriminator takes images, determines if fake  Train both at same time – generator learns to fool discriminator
  • 49. … in CNTK def convolutional_generator(z): … h2 = C.layers.ConvolutionTranspose2D(gkernel, num_filters=gf_dim*2, strides=gstride, pad=True, output_shape=(s_h2, s_w2), activation=None)(h1) … return C.reshape(h3, img_h * img_w)
  • 50. Super Resolution GANs  GANs Up-res images  Just shown small and large versions so training data is easy https://arxiv.org/pdf/1609.04802.pdf
  • 51. GANs on Steroids  CycleGANs is currently the best  GANs fighting GANs  Changing so fast it has its own zoo  https://www.youtube.com/watch?v=IbjF5VjniVE  Yann LeCun says  “The most important idea in ML in the last 10 years”
  • 52. How fast are GANs changing? Credit: Bruno Gavranović
  • 54.
  • 55. Neural Networks Can Be Fooled  https://blog.openai.com/adversarial-example-research/  Networks are learning a large non-linear equation  “Intelligent” noise finds “alternate” solution
  • 56. Regulations, Liability, Social Issues  NNs doing medical diagnoses  How do you regulate? If it’s wrong, where does the fault lie?  Garbage in, garbage out  FaceApp “Whitewashing”  Economic Displacement  Job losses  Privacy  Better, faster facial recognition, voiceprinting  #FakeNews  Autogeneration of fake audio, video
  • 57.
  • 58. Deep Learning Toolkits  CNTK  1-bit SGD for better distributed training  TensorFlow  Momentum  Chainer  Torch  Caffe  MXNet  Azure Linux and Windows GPU VMs
  • 59.
  • 60. What Does the Future Hold?  Adversaries  Adversarial networks  Adversarial examples  Reinforcement  Deep RL  “Training” DL  Mixture of Networks  RNNs + CNNs  Conv + Deconv
  • 61. Call to action  CNTK Tutorials  In GitHub: https://aka.ms/cntk_tut  On Notebooks.azure.com/cntk  Finding the latest papers  arXiv (https://arxiv.org/) …  And even more important arXiv Sanity Preserver: http://www.arxiv- sanity.com/  Re-visit de:code session recordings on Channel 9.  Continue your education at Microsoft Virtual Academy online.