SlideShare una empresa de Scribd logo
1 de 55
Autoencoders for Image
Classification
Bartosz Witkowski
Jagiellonian University
Faculty of Mathematics and Computer Science
INSTITUTE OF COMPUTER SCIENCE
Contents
• Theoretical Background
• Problem Formulation
• Methodology
• Results
Theoretıcal Background
• Artificial Neural Networks
• Deep Neural Networks and Deep Learning
• Autoencoders and Sparsity
• Convolutional Networks
artificial neural networks
• The central idea is to extract linear
combinations of the inputs as derived features
and then model the target as a nonlinear
function of these features
• A feedforward neural network of depth n is a n-
stage regression or classification model,
The outputs of layer l are called activations and are
computed based on linear combinations of inputs
and the bias unit in the following way:
Encoding
Decoding
soft-max activation function used as the
last layer (classifier) for K-class
classification
Two types of activation functions:
sigmoid activation and soft-max
activation
When training feedforward networks we
use an average sum-of-squared errors as
an error function
To prevent from overfitting we add regularization
to error function
deep neural networks and
deep learning
• Deep vanilla neural networks perform worse
than neural networks with one or two hidden
layers.
• In theory deep neural networks have at least
the same expressive power as shallow neural
networks but in practice they stuck in local
optima during training phase.
• It is important to use a non-linear activation
function f(x) in each hidden layer
autoencoders and sparsity
• An autoencoder is a neural network that is
trained to encode an input x into some
representation c(x) so that the input can be
reconstructed from that representation
After successful3 training,
it should decompose
the inputs into a
combination of
hidden layer activations.
With this trained
autoencoder has learned
features
We can measure the average activations of the
neurons in the second layer:
and add a penalty to the error function which will prevent
the activations from straying too far from some desired
mean activation p (the sparsity parameter).
* Kullback-Leibler divergence
The resulting autoencoder is called a sparse
autoencoder.
B is called the sparsity constraint and controls
the sparsity penalty.
stacked autoencoders
convolutional networks
• Better than vanilla neural network.
• Inspired by the human visual system structure
and work by exploiting local connections
through two operations ( Convolution and Sub-
sampling / Pooling)
convolution
• Organized in layers of two types:
• Convolution, Sub-sampling
pooling
• Biologically inspired operation that reduces the
dimensionality of the input.
Single cell of output matrix is calculated by:
kernel, I is the input matrix. In actual implementation P
problem Formulation
• MNIST
Dataset: Handwritten digits,
Training Set: 60,000 examples
Test Set: 10,000 examples
Size: 28 x 28
methodology
• Architecture-1 Stacked Autoencoders
• Artchitecture-2 Stacked Convolutional
Autoencoders
• Visualizing Features
architecture-1
• 784-200-200-200-10 Deep network
• Greedy layerwise training
• Training protocol
• Training Parameters and Methods
greedy layer wise training
• to construct a deep pretrained network of n
layers divide the learning into n stages.
• In the first stage train an autoencoder on the
provided training data sans labels.
• Next map the training data to the feature space.
• The mapped data is then used to train the next
stage auto encoder.
• The training follows layer by layer until the last
one.
• The last layer is trained as a classifier (not as an
autoencoder) using supervised learning.
training protocol
t: the first 30000 images (out of 60000
After training the last stage, the networks n1 through n4
are stacked to form a deep neural network. Use the full
training set to train the deep neural network – this final
step is called fine-tuning.
modify the weights W(1) as well, so that adjustments can be m
archıtecture-2
• Instead of training the network on the full
image we can exploit local connectivity via
convolutional networks, and additionally
restrict the number of trainable parameters
with the use of pooling.
visualizing features
Activation of the hidden unit i
Results
difference of cnns and
autoencoders
• The main difference between AutoEncoder and
Convolutional Network is the level of network hardwiring.
Convolutional Nets are pretty much hardwired. Convolution
operation is pretty much local in image domain, meaning
much more sparsity in the number of connections in neural
network view. Pooling(subsampling) operation in image
domain is also a hardwired set of neural connections in
neural domain. Such topological constraints on network
structure. Given such constraints, training of CNN learns
best weights for this convolution operation (In practice there
are multiple filters). CNNs are usually used for image and
speech tasks where convolutional constraints are a good
assumption.
• In contrast, Autoencoders almost specify
nothing about the topology of the network.
They are much more general. The idea is to
find good neural transformation to reconstruct
the input. They are composed of encoder
(projects the input to hidden layer) and
decoder (reprojects hidden layer to output).
The hidden layer learns a set of latent features
or latent factors. Linear autoencoders span the
same subspace with PCA. Given a dataset,
they learn number of basis to explain the
underlying pattern of the data.
Cenk Bircanoğlu
“Thank You For Listening”

Más contenido relacionado

La actualidad más candente

Intro to Deep Learning
Intro to Deep LearningIntro to Deep Learning
Intro to Deep LearningKushal Arora
 
Artificial neural network
Artificial neural networkArtificial neural network
Artificial neural networkDEEPASHRI HK
 
Introduction to un supervised learning
Introduction to un supervised learningIntroduction to un supervised learning
Introduction to un supervised learningRishikesh .
 
Nural network ER. Abhishek k. upadhyay
Nural network ER. Abhishek  k. upadhyayNural network ER. Abhishek  k. upadhyay
Nural network ER. Abhishek k. upadhyayabhishek upadhyay
 
Artificial neural network for concrete mix design
Artificial neural network for concrete mix designArtificial neural network for concrete mix design
Artificial neural network for concrete mix designMonjurul Shuvo
 
Deep Style: Using Variational Auto-encoders for Image Generation
Deep Style: Using Variational Auto-encoders for Image GenerationDeep Style: Using Variational Auto-encoders for Image Generation
Deep Style: Using Variational Auto-encoders for Image GenerationTJ Torres
 
introduction to deep Learning with full detail
introduction to deep Learning with full detailintroduction to deep Learning with full detail
introduction to deep Learning with full detailsonykhan3
 
Artificial neural networks
Artificial neural networksArtificial neural networks
Artificial neural networksmadhu sudhakar
 
Machine Learning: Introduction to Neural Networks
Machine Learning: Introduction to Neural NetworksMachine Learning: Introduction to Neural Networks
Machine Learning: Introduction to Neural NetworksFrancesco Collova'
 
Fundamental, An Introduction to Neural Networks
Fundamental, An Introduction to Neural NetworksFundamental, An Introduction to Neural Networks
Fundamental, An Introduction to Neural NetworksNelson Piedra
 
Neural network
Neural networkNeural network
Neural networkFacebook
 
(Artificial) Neural Network
(Artificial) Neural Network(Artificial) Neural Network
(Artificial) Neural NetworkPutri Wikie
 
Artificial neural networks
Artificial neural networksArtificial neural networks
Artificial neural networksernj
 

La actualidad más candente (20)

Intro to Deep Learning
Intro to Deep LearningIntro to Deep Learning
Intro to Deep Learning
 
Artificial neural network
Artificial neural networkArtificial neural network
Artificial neural network
 
Introduction to un supervised learning
Introduction to un supervised learningIntroduction to un supervised learning
Introduction to un supervised learning
 
Nural network ER. Abhishek k. upadhyay
Nural network ER. Abhishek  k. upadhyayNural network ER. Abhishek  k. upadhyay
Nural network ER. Abhishek k. upadhyay
 
Artificial neural network for concrete mix design
Artificial neural network for concrete mix designArtificial neural network for concrete mix design
Artificial neural network for concrete mix design
 
Artificial Neuron network
Artificial Neuron network Artificial Neuron network
Artificial Neuron network
 
Deep Style: Using Variational Auto-encoders for Image Generation
Deep Style: Using Variational Auto-encoders for Image GenerationDeep Style: Using Variational Auto-encoders for Image Generation
Deep Style: Using Variational Auto-encoders for Image Generation
 
introduction to deep Learning with full detail
introduction to deep Learning with full detailintroduction to deep Learning with full detail
introduction to deep Learning with full detail
 
Artificial neural network
Artificial neural networkArtificial neural network
Artificial neural network
 
Artificial neural networks
Artificial neural networksArtificial neural networks
Artificial neural networks
 
Machine Learning: Introduction to Neural Networks
Machine Learning: Introduction to Neural NetworksMachine Learning: Introduction to Neural Networks
Machine Learning: Introduction to Neural Networks
 
Fundamental, An Introduction to Neural Networks
Fundamental, An Introduction to Neural NetworksFundamental, An Introduction to Neural Networks
Fundamental, An Introduction to Neural Networks
 
Neural network
Neural networkNeural network
Neural network
 
Artifical Neural Network
Artifical Neural NetworkArtifical Neural Network
Artifical Neural Network
 
Deep Learning
Deep Learning Deep Learning
Deep Learning
 
Neural networks introduction
Neural networks introductionNeural networks introduction
Neural networks introduction
 
Neural network
Neural networkNeural network
Neural network
 
(Artificial) Neural Network
(Artificial) Neural Network(Artificial) Neural Network
(Artificial) Neural Network
 
Artificial neural networks
Artificial neural networksArtificial neural networks
Artificial neural networks
 
Intoduction to Neural Network
Intoduction to Neural NetworkIntoduction to Neural Network
Intoduction to Neural Network
 

Similar a Autoencoders for image_classification

Fundamental of deep learning
Fundamental of deep learningFundamental of deep learning
Fundamental of deep learningStanley Wang
 
Handwritten Digit Recognition using Convolutional Neural Networks
Handwritten Digit Recognition using Convolutional Neural  NetworksHandwritten Digit Recognition using Convolutional Neural  Networks
Handwritten Digit Recognition using Convolutional Neural NetworksIRJET Journal
 
Handwritten Digit Recognition(Convolutional Neural Network) PPT
Handwritten Digit Recognition(Convolutional Neural Network) PPTHandwritten Digit Recognition(Convolutional Neural Network) PPT
Handwritten Digit Recognition(Convolutional Neural Network) PPTRishabhTyagi48
 
International Journal of Computational Engineering Research(IJCER)
International Journal of Computational Engineering Research(IJCER)International Journal of Computational Engineering Research(IJCER)
International Journal of Computational Engineering Research(IJCER)ijceronline
 
Deep learning from a novice perspective
Deep learning from a novice perspectiveDeep learning from a novice perspective
Deep learning from a novice perspectiveAnirban Santara
 
FINAL_Team_4.pptx
FINAL_Team_4.pptxFINAL_Team_4.pptx
FINAL_Team_4.pptxnitin571047
 
International Journal of Computational Engineering Research(IJCER)
International Journal of Computational Engineering Research(IJCER)International Journal of Computational Engineering Research(IJCER)
International Journal of Computational Engineering Research(IJCER)ijceronline
 
Neural Networks in Data Mining - “An Overview”
Neural Networks  in Data Mining -   “An Overview”Neural Networks  in Data Mining -   “An Overview”
Neural Networks in Data Mining - “An Overview”Dr.(Mrs).Gethsiyal Augasta
 
DSRLab seminar Introduction to deep learning
DSRLab seminar   Introduction to deep learningDSRLab seminar   Introduction to deep learning
DSRLab seminar Introduction to deep learningPoo Kuan Hoong
 
Deep Neural Networks (D1L2 Insight@DCU Machine Learning Workshop 2017)
Deep Neural Networks (D1L2 Insight@DCU Machine Learning Workshop 2017)Deep Neural Networks (D1L2 Insight@DCU Machine Learning Workshop 2017)
Deep Neural Networks (D1L2 Insight@DCU Machine Learning Workshop 2017)Universitat Politècnica de Catalunya
 
A Survey of Convolutional Neural Networks
A Survey of Convolutional Neural NetworksA Survey of Convolutional Neural Networks
A Survey of Convolutional Neural NetworksRimzim Thube
 
Convolutional neural networks 이론과 응용
Convolutional neural networks 이론과 응용Convolutional neural networks 이론과 응용
Convolutional neural networks 이론과 응용홍배 김
 
Cvpr 2018 papers review (efficient computing)
Cvpr 2018 papers review (efficient computing)Cvpr 2018 papers review (efficient computing)
Cvpr 2018 papers review (efficient computing)DonghyunKang12
 
Convolutional Neural Network and Its Applications
Convolutional Neural Network and Its ApplicationsConvolutional Neural Network and Its Applications
Convolutional Neural Network and Its ApplicationsKasun Chinthaka Piyarathna
 
Basics of Artificial Neural Network
Basics of Artificial Neural Network Basics of Artificial Neural Network
Basics of Artificial Neural Network Subham Preetam
 
Easily Trainable Neural Network Using TransferLearning
Easily Trainable Neural Network Using TransferLearningEasily Trainable Neural Network Using TransferLearning
Easily Trainable Neural Network Using TransferLearningIRJET Journal
 

Similar a Autoencoders for image_classification (20)

Fundamental of deep learning
Fundamental of deep learningFundamental of deep learning
Fundamental of deep learning
 
Handwritten Digit Recognition using Convolutional Neural Networks
Handwritten Digit Recognition using Convolutional Neural  NetworksHandwritten Digit Recognition using Convolutional Neural  Networks
Handwritten Digit Recognition using Convolutional Neural Networks
 
Handwritten Digit Recognition(Convolutional Neural Network) PPT
Handwritten Digit Recognition(Convolutional Neural Network) PPTHandwritten Digit Recognition(Convolutional Neural Network) PPT
Handwritten Digit Recognition(Convolutional Neural Network) PPT
 
International Journal of Computational Engineering Research(IJCER)
International Journal of Computational Engineering Research(IJCER)International Journal of Computational Engineering Research(IJCER)
International Journal of Computational Engineering Research(IJCER)
 
Deep Learning
Deep LearningDeep Learning
Deep Learning
 
Deep learning from a novice perspective
Deep learning from a novice perspectiveDeep learning from a novice perspective
Deep learning from a novice perspective
 
FINAL_Team_4.pptx
FINAL_Team_4.pptxFINAL_Team_4.pptx
FINAL_Team_4.pptx
 
International Journal of Computational Engineering Research(IJCER)
International Journal of Computational Engineering Research(IJCER)International Journal of Computational Engineering Research(IJCER)
International Journal of Computational Engineering Research(IJCER)
 
Neural Networks in Data Mining - “An Overview”
Neural Networks  in Data Mining -   “An Overview”Neural Networks  in Data Mining -   “An Overview”
Neural Networks in Data Mining - “An Overview”
 
Deep Learning
Deep LearningDeep Learning
Deep Learning
 
DSRLab seminar Introduction to deep learning
DSRLab seminar   Introduction to deep learningDSRLab seminar   Introduction to deep learning
DSRLab seminar Introduction to deep learning
 
Deep Neural Networks (D1L2 Insight@DCU Machine Learning Workshop 2017)
Deep Neural Networks (D1L2 Insight@DCU Machine Learning Workshop 2017)Deep Neural Networks (D1L2 Insight@DCU Machine Learning Workshop 2017)
Deep Neural Networks (D1L2 Insight@DCU Machine Learning Workshop 2017)
 
A Survey of Convolutional Neural Networks
A Survey of Convolutional Neural NetworksA Survey of Convolutional Neural Networks
A Survey of Convolutional Neural Networks
 
Convolutional neural networks 이론과 응용
Convolutional neural networks 이론과 응용Convolutional neural networks 이론과 응용
Convolutional neural networks 이론과 응용
 
Cvpr 2018 papers review (efficient computing)
Cvpr 2018 papers review (efficient computing)Cvpr 2018 papers review (efficient computing)
Cvpr 2018 papers review (efficient computing)
 
Convolutional Neural Network and Its Applications
Convolutional Neural Network and Its ApplicationsConvolutional Neural Network and Its Applications
Convolutional Neural Network and Its Applications
 
DL.pdf
DL.pdfDL.pdf
DL.pdf
 
Basics of Artificial Neural Network
Basics of Artificial Neural Network Basics of Artificial Neural Network
Basics of Artificial Neural Network
 
CNN.pptx.pdf
CNN.pptx.pdfCNN.pptx.pdf
CNN.pptx.pdf
 
Easily Trainable Neural Network Using TransferLearning
Easily Trainable Neural Network Using TransferLearningEasily Trainable Neural Network Using TransferLearning
Easily Trainable Neural Network Using TransferLearning
 

Más de Cenk Bircanoğlu

Yapay Sinir Ağlarında Aktivasyon Fonksiyonlarının Karşılaştırılması
Yapay Sinir Ağlarında Aktivasyon Fonksiyonlarının KarşılaştırılmasıYapay Sinir Ağlarında Aktivasyon Fonksiyonlarının Karşılaştırılması
Yapay Sinir Ağlarında Aktivasyon Fonksiyonlarının KarşılaştırılmasıCenk Bircanoğlu
 
Image Generation with Tensorflow
Image Generation with TensorflowImage Generation with Tensorflow
Image Generation with TensorflowCenk Bircanoğlu
 
Kaggles House Prices Competition Study
Kaggles House Prices Competition StudyKaggles House Prices Competition Study
Kaggles House Prices Competition StudyCenk Bircanoğlu
 
Routing or Computing? The Paradigm Shift Towards Intelligent Computer Network...
Routing or Computing? The Paradigm Shift Towards Intelligent Computer Network...Routing or Computing? The Paradigm Shift Towards Intelligent Computer Network...
Routing or Computing? The Paradigm Shift Towards Intelligent Computer Network...Cenk Bircanoğlu
 
Facial Emotion Classification Using Deep Embedding with Triplet Loss Function
Facial Emotion Classification Using Deep Embedding with Triplet Loss FunctionFacial Emotion Classification Using Deep Embedding with Triplet Loss Function
Facial Emotion Classification Using Deep Embedding with Triplet Loss FunctionCenk Bircanoğlu
 
A Comparison of Loss Function on Deep Embedding
A Comparison of Loss Function on Deep EmbeddingA Comparison of Loss Function on Deep Embedding
A Comparison of Loss Function on Deep EmbeddingCenk Bircanoğlu
 

Más de Cenk Bircanoğlu (7)

Yapay Sinir Ağlarında Aktivasyon Fonksiyonlarının Karşılaştırılması
Yapay Sinir Ağlarında Aktivasyon Fonksiyonlarının KarşılaştırılmasıYapay Sinir Ağlarında Aktivasyon Fonksiyonlarının Karşılaştırılması
Yapay Sinir Ağlarında Aktivasyon Fonksiyonlarının Karşılaştırılması
 
Image Generation with Tensorflow
Image Generation with TensorflowImage Generation with Tensorflow
Image Generation with Tensorflow
 
Kaggles House Prices Competition Study
Kaggles House Prices Competition StudyKaggles House Prices Competition Study
Kaggles House Prices Competition Study
 
Routing or Computing? The Paradigm Shift Towards Intelligent Computer Network...
Routing or Computing? The Paradigm Shift Towards Intelligent Computer Network...Routing or Computing? The Paradigm Shift Towards Intelligent Computer Network...
Routing or Computing? The Paradigm Shift Towards Intelligent Computer Network...
 
Facial Emotion Classification Using Deep Embedding with Triplet Loss Function
Facial Emotion Classification Using Deep Embedding with Triplet Loss FunctionFacial Emotion Classification Using Deep Embedding with Triplet Loss Function
Facial Emotion Classification Using Deep Embedding with Triplet Loss Function
 
Recommendation Systems
Recommendation SystemsRecommendation Systems
Recommendation Systems
 
A Comparison of Loss Function on Deep Embedding
A Comparison of Loss Function on Deep EmbeddingA Comparison of Loss Function on Deep Embedding
A Comparison of Loss Function on Deep Embedding
 

Último

%in kaalfontein+277-882-255-28 abortion pills for sale in kaalfontein
%in kaalfontein+277-882-255-28 abortion pills for sale in kaalfontein%in kaalfontein+277-882-255-28 abortion pills for sale in kaalfontein
%in kaalfontein+277-882-255-28 abortion pills for sale in kaalfonteinmasabamasaba
 
WSO2CON2024 - It's time to go Platformless
WSO2CON2024 - It's time to go PlatformlessWSO2CON2024 - It's time to go Platformless
WSO2CON2024 - It's time to go PlatformlessWSO2
 
WSO2CON 2024 - Does Open Source Still Matter?
WSO2CON 2024 - Does Open Source Still Matter?WSO2CON 2024 - Does Open Source Still Matter?
WSO2CON 2024 - Does Open Source Still Matter?WSO2
 
%in Midrand+277-882-255-28 abortion pills for sale in midrand
%in Midrand+277-882-255-28 abortion pills for sale in midrand%in Midrand+277-882-255-28 abortion pills for sale in midrand
%in Midrand+277-882-255-28 abortion pills for sale in midrandmasabamasaba
 
%in Soweto+277-882-255-28 abortion pills for sale in soweto
%in Soweto+277-882-255-28 abortion pills for sale in soweto%in Soweto+277-882-255-28 abortion pills for sale in soweto
%in Soweto+277-882-255-28 abortion pills for sale in sowetomasabamasaba
 
Crypto Cloud Review - How To Earn Up To $500 Per DAY Of Bitcoin 100% On AutoP...
Crypto Cloud Review - How To Earn Up To $500 Per DAY Of Bitcoin 100% On AutoP...Crypto Cloud Review - How To Earn Up To $500 Per DAY Of Bitcoin 100% On AutoP...
Crypto Cloud Review - How To Earn Up To $500 Per DAY Of Bitcoin 100% On AutoP...SelfMade bd
 
Artyushina_Guest lecture_YorkU CS May 2024.pptx
Artyushina_Guest lecture_YorkU CS May 2024.pptxArtyushina_Guest lecture_YorkU CS May 2024.pptx
Artyushina_Guest lecture_YorkU CS May 2024.pptxAnnaArtyushina1
 
Shapes for Sharing between Graph Data Spaces - and Epistemic Querying of RDF-...
Shapes for Sharing between Graph Data Spaces - and Epistemic Querying of RDF-...Shapes for Sharing between Graph Data Spaces - and Epistemic Querying of RDF-...
Shapes for Sharing between Graph Data Spaces - and Epistemic Querying of RDF-...Steffen Staab
 
+971565801893>>SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHAB...
+971565801893>>SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHAB...+971565801893>>SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHAB...
+971565801893>>SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHAB...Health
 
%in kempton park+277-882-255-28 abortion pills for sale in kempton park
%in kempton park+277-882-255-28 abortion pills for sale in kempton park %in kempton park+277-882-255-28 abortion pills for sale in kempton park
%in kempton park+277-882-255-28 abortion pills for sale in kempton park masabamasaba
 
%+27788225528 love spells in Huntington Beach Psychic Readings, Attraction sp...
%+27788225528 love spells in Huntington Beach Psychic Readings, Attraction sp...%+27788225528 love spells in Huntington Beach Psychic Readings, Attraction sp...
%+27788225528 love spells in Huntington Beach Psychic Readings, Attraction sp...masabamasaba
 
VTU technical seminar 8Th Sem on Scikit-learn
VTU technical seminar 8Th Sem on Scikit-learnVTU technical seminar 8Th Sem on Scikit-learn
VTU technical seminar 8Th Sem on Scikit-learnAmarnathKambale
 
WSO2Con2024 - From Code To Cloud: Fast Track Your Cloud Native Journey with C...
WSO2Con2024 - From Code To Cloud: Fast Track Your Cloud Native Journey with C...WSO2Con2024 - From Code To Cloud: Fast Track Your Cloud Native Journey with C...
WSO2Con2024 - From Code To Cloud: Fast Track Your Cloud Native Journey with C...WSO2
 
W01_panagenda_Navigating-the-Future-with-The-Hitchhikers-Guide-to-Notes-and-D...
W01_panagenda_Navigating-the-Future-with-The-Hitchhikers-Guide-to-Notes-and-D...W01_panagenda_Navigating-the-Future-with-The-Hitchhikers-Guide-to-Notes-and-D...
W01_panagenda_Navigating-the-Future-with-The-Hitchhikers-Guide-to-Notes-and-D...panagenda
 
Large-scale Logging Made Easy: Meetup at Deutsche Bank 2024
Large-scale Logging Made Easy: Meetup at Deutsche Bank 2024Large-scale Logging Made Easy: Meetup at Deutsche Bank 2024
Large-scale Logging Made Easy: Meetup at Deutsche Bank 2024VictoriaMetrics
 
What Goes Wrong with Language Definitions and How to Improve the Situation
What Goes Wrong with Language Definitions and How to Improve the SituationWhat Goes Wrong with Language Definitions and How to Improve the Situation
What Goes Wrong with Language Definitions and How to Improve the SituationJuha-Pekka Tolvanen
 
%in Bahrain+277-882-255-28 abortion pills for sale in Bahrain
%in Bahrain+277-882-255-28 abortion pills for sale in Bahrain%in Bahrain+277-882-255-28 abortion pills for sale in Bahrain
%in Bahrain+277-882-255-28 abortion pills for sale in Bahrainmasabamasaba
 
Payment Gateway Testing Simplified_ A Step-by-Step Guide for Beginners.pdf
Payment Gateway Testing Simplified_ A Step-by-Step Guide for Beginners.pdfPayment Gateway Testing Simplified_ A Step-by-Step Guide for Beginners.pdf
Payment Gateway Testing Simplified_ A Step-by-Step Guide for Beginners.pdfkalichargn70th171
 
%+27788225528 love spells in Boston Psychic Readings, Attraction spells,Bring...
%+27788225528 love spells in Boston Psychic Readings, Attraction spells,Bring...%+27788225528 love spells in Boston Psychic Readings, Attraction spells,Bring...
%+27788225528 love spells in Boston Psychic Readings, Attraction spells,Bring...masabamasaba
 

Último (20)

%in kaalfontein+277-882-255-28 abortion pills for sale in kaalfontein
%in kaalfontein+277-882-255-28 abortion pills for sale in kaalfontein%in kaalfontein+277-882-255-28 abortion pills for sale in kaalfontein
%in kaalfontein+277-882-255-28 abortion pills for sale in kaalfontein
 
WSO2CON2024 - It's time to go Platformless
WSO2CON2024 - It's time to go PlatformlessWSO2CON2024 - It's time to go Platformless
WSO2CON2024 - It's time to go Platformless
 
WSO2CON 2024 - Does Open Source Still Matter?
WSO2CON 2024 - Does Open Source Still Matter?WSO2CON 2024 - Does Open Source Still Matter?
WSO2CON 2024 - Does Open Source Still Matter?
 
%in Midrand+277-882-255-28 abortion pills for sale in midrand
%in Midrand+277-882-255-28 abortion pills for sale in midrand%in Midrand+277-882-255-28 abortion pills for sale in midrand
%in Midrand+277-882-255-28 abortion pills for sale in midrand
 
%in Soweto+277-882-255-28 abortion pills for sale in soweto
%in Soweto+277-882-255-28 abortion pills for sale in soweto%in Soweto+277-882-255-28 abortion pills for sale in soweto
%in Soweto+277-882-255-28 abortion pills for sale in soweto
 
Crypto Cloud Review - How To Earn Up To $500 Per DAY Of Bitcoin 100% On AutoP...
Crypto Cloud Review - How To Earn Up To $500 Per DAY Of Bitcoin 100% On AutoP...Crypto Cloud Review - How To Earn Up To $500 Per DAY Of Bitcoin 100% On AutoP...
Crypto Cloud Review - How To Earn Up To $500 Per DAY Of Bitcoin 100% On AutoP...
 
Artyushina_Guest lecture_YorkU CS May 2024.pptx
Artyushina_Guest lecture_YorkU CS May 2024.pptxArtyushina_Guest lecture_YorkU CS May 2024.pptx
Artyushina_Guest lecture_YorkU CS May 2024.pptx
 
Shapes for Sharing between Graph Data Spaces - and Epistemic Querying of RDF-...
Shapes for Sharing between Graph Data Spaces - and Epistemic Querying of RDF-...Shapes for Sharing between Graph Data Spaces - and Epistemic Querying of RDF-...
Shapes for Sharing between Graph Data Spaces - and Epistemic Querying of RDF-...
 
+971565801893>>SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHAB...
+971565801893>>SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHAB...+971565801893>>SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHAB...
+971565801893>>SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHAB...
 
%in kempton park+277-882-255-28 abortion pills for sale in kempton park
%in kempton park+277-882-255-28 abortion pills for sale in kempton park %in kempton park+277-882-255-28 abortion pills for sale in kempton park
%in kempton park+277-882-255-28 abortion pills for sale in kempton park
 
%+27788225528 love spells in Huntington Beach Psychic Readings, Attraction sp...
%+27788225528 love spells in Huntington Beach Psychic Readings, Attraction sp...%+27788225528 love spells in Huntington Beach Psychic Readings, Attraction sp...
%+27788225528 love spells in Huntington Beach Psychic Readings, Attraction sp...
 
VTU technical seminar 8Th Sem on Scikit-learn
VTU technical seminar 8Th Sem on Scikit-learnVTU technical seminar 8Th Sem on Scikit-learn
VTU technical seminar 8Th Sem on Scikit-learn
 
WSO2Con2024 - From Code To Cloud: Fast Track Your Cloud Native Journey with C...
WSO2Con2024 - From Code To Cloud: Fast Track Your Cloud Native Journey with C...WSO2Con2024 - From Code To Cloud: Fast Track Your Cloud Native Journey with C...
WSO2Con2024 - From Code To Cloud: Fast Track Your Cloud Native Journey with C...
 
W01_panagenda_Navigating-the-Future-with-The-Hitchhikers-Guide-to-Notes-and-D...
W01_panagenda_Navigating-the-Future-with-The-Hitchhikers-Guide-to-Notes-and-D...W01_panagenda_Navigating-the-Future-with-The-Hitchhikers-Guide-to-Notes-and-D...
W01_panagenda_Navigating-the-Future-with-The-Hitchhikers-Guide-to-Notes-and-D...
 
Large-scale Logging Made Easy: Meetup at Deutsche Bank 2024
Large-scale Logging Made Easy: Meetup at Deutsche Bank 2024Large-scale Logging Made Easy: Meetup at Deutsche Bank 2024
Large-scale Logging Made Easy: Meetup at Deutsche Bank 2024
 
Microsoft AI Transformation Partner Playbook.pdf
Microsoft AI Transformation Partner Playbook.pdfMicrosoft AI Transformation Partner Playbook.pdf
Microsoft AI Transformation Partner Playbook.pdf
 
What Goes Wrong with Language Definitions and How to Improve the Situation
What Goes Wrong with Language Definitions and How to Improve the SituationWhat Goes Wrong with Language Definitions and How to Improve the Situation
What Goes Wrong with Language Definitions and How to Improve the Situation
 
%in Bahrain+277-882-255-28 abortion pills for sale in Bahrain
%in Bahrain+277-882-255-28 abortion pills for sale in Bahrain%in Bahrain+277-882-255-28 abortion pills for sale in Bahrain
%in Bahrain+277-882-255-28 abortion pills for sale in Bahrain
 
Payment Gateway Testing Simplified_ A Step-by-Step Guide for Beginners.pdf
Payment Gateway Testing Simplified_ A Step-by-Step Guide for Beginners.pdfPayment Gateway Testing Simplified_ A Step-by-Step Guide for Beginners.pdf
Payment Gateway Testing Simplified_ A Step-by-Step Guide for Beginners.pdf
 
%+27788225528 love spells in Boston Psychic Readings, Attraction spells,Bring...
%+27788225528 love spells in Boston Psychic Readings, Attraction spells,Bring...%+27788225528 love spells in Boston Psychic Readings, Attraction spells,Bring...
%+27788225528 love spells in Boston Psychic Readings, Attraction spells,Bring...
 

Autoencoders for image_classification

  • 1. Autoencoders for Image Classification Bartosz Witkowski Jagiellonian University Faculty of Mathematics and Computer Science INSTITUTE OF COMPUTER SCIENCE
  • 2. Contents • Theoretical Background • Problem Formulation • Methodology • Results
  • 3.
  • 4.
  • 5.
  • 6. Theoretıcal Background • Artificial Neural Networks • Deep Neural Networks and Deep Learning • Autoencoders and Sparsity • Convolutional Networks
  • 7. artificial neural networks • The central idea is to extract linear combinations of the inputs as derived features and then model the target as a nonlinear function of these features • A feedforward neural network of depth n is a n- stage regression or classification model,
  • 8.
  • 9. The outputs of layer l are called activations and are computed based on linear combinations of inputs and the bias unit in the following way: Encoding Decoding
  • 10. soft-max activation function used as the last layer (classifier) for K-class classification Two types of activation functions: sigmoid activation and soft-max activation
  • 11. When training feedforward networks we use an average sum-of-squared errors as an error function To prevent from overfitting we add regularization to error function
  • 12. deep neural networks and deep learning • Deep vanilla neural networks perform worse than neural networks with one or two hidden layers. • In theory deep neural networks have at least the same expressive power as shallow neural networks but in practice they stuck in local optima during training phase. • It is important to use a non-linear activation function f(x) in each hidden layer
  • 13. autoencoders and sparsity • An autoencoder is a neural network that is trained to encode an input x into some representation c(x) so that the input can be reconstructed from that representation
  • 14.
  • 15. After successful3 training, it should decompose the inputs into a combination of hidden layer activations. With this trained autoencoder has learned features
  • 16. We can measure the average activations of the neurons in the second layer: and add a penalty to the error function which will prevent the activations from straying too far from some desired mean activation p (the sparsity parameter). * Kullback-Leibler divergence
  • 17.
  • 18. The resulting autoencoder is called a sparse autoencoder. B is called the sparsity constraint and controls the sparsity penalty.
  • 20.
  • 21.
  • 22.
  • 23.
  • 24. convolutional networks • Better than vanilla neural network. • Inspired by the human visual system structure and work by exploiting local connections through two operations ( Convolution and Sub- sampling / Pooling)
  • 25. convolution • Organized in layers of two types: • Convolution, Sub-sampling
  • 26.
  • 27. pooling • Biologically inspired operation that reduces the dimensionality of the input.
  • 28. Single cell of output matrix is calculated by: kernel, I is the input matrix. In actual implementation P
  • 29.
  • 31. Dataset: Handwritten digits, Training Set: 60,000 examples Test Set: 10,000 examples Size: 28 x 28
  • 32.
  • 33. methodology • Architecture-1 Stacked Autoencoders • Artchitecture-2 Stacked Convolutional Autoencoders • Visualizing Features
  • 34. architecture-1 • 784-200-200-200-10 Deep network • Greedy layerwise training • Training protocol • Training Parameters and Methods
  • 35. greedy layer wise training • to construct a deep pretrained network of n layers divide the learning into n stages. • In the first stage train an autoencoder on the provided training data sans labels. • Next map the training data to the feature space. • The mapped data is then used to train the next stage auto encoder. • The training follows layer by layer until the last one. • The last layer is trained as a classifier (not as an autoencoder) using supervised learning.
  • 37.
  • 38. t: the first 30000 images (out of 60000
  • 39.
  • 40. After training the last stage, the networks n1 through n4 are stacked to form a deep neural network. Use the full training set to train the deep neural network – this final step is called fine-tuning.
  • 41. modify the weights W(1) as well, so that adjustments can be m
  • 42. archıtecture-2 • Instead of training the network on the full image we can exploit local connectivity via convolutional networks, and additionally restrict the number of trainable parameters with the use of pooling.
  • 43.
  • 44.
  • 45.
  • 46.
  • 49.
  • 50.
  • 51.
  • 52.
  • 53. difference of cnns and autoencoders • The main difference between AutoEncoder and Convolutional Network is the level of network hardwiring. Convolutional Nets are pretty much hardwired. Convolution operation is pretty much local in image domain, meaning much more sparsity in the number of connections in neural network view. Pooling(subsampling) operation in image domain is also a hardwired set of neural connections in neural domain. Such topological constraints on network structure. Given such constraints, training of CNN learns best weights for this convolution operation (In practice there are multiple filters). CNNs are usually used for image and speech tasks where convolutional constraints are a good assumption.
  • 54. • In contrast, Autoencoders almost specify nothing about the topology of the network. They are much more general. The idea is to find good neural transformation to reconstruct the input. They are composed of encoder (projects the input to hidden layer) and decoder (reprojects hidden layer to output). The hidden layer learns a set of latent features or latent factors. Linear autoencoders span the same subspace with PCA. Given a dataset, they learn number of basis to explain the underlying pattern of the data.
  • 55. Cenk Bircanoğlu “Thank You For Listening”