SlideShare a Scribd company logo
Image Classification with
Deep Neural Networks
Yogendra Tamang
Sabin Devkota
Presented By:
February 6, 2016
ImageNet Classification with Deep Convolutional Neural Networks
A. Krizhevsky, I. Sutskever, G. Hinton
#pwlnepal
PWL Kathmandu
Papers We Love
Kathmandu
Outline
Background
Image Classification
Activation Functions
Convolution Neural Networks
Other Issues
Techniques used in other papers
And So on…
Background
Learning
Supervised
Unsupervised
AI Tasks
Classification and Regression
Clustering
Machine Learning Problem
Supervised
Regression
Classfication
Unsupervised
Clustering
Background
Classification
 Classifies data into one of discrete classes
 Eg. Classifying digits
 Cost Function for Classification Task may be Logistic Regression or Log-likelihood
Regression
 Predicts continuous real valued output
 Eg. Stock Price Predictions
 Cost function for regression type problem are MSE(Mean Squared Error)
Introduction
• Input Image is array of
number for computer
• Assign a label to input image
from set of categories
• One of core problems in
computer vision
Neural Networks and Multilayer Perceptrons
Neural Networks and Multi Layer Perceptrons
“activation” of unit in layer
matrix of weights controlling
function mapping from layer to
layer
They use Activation Functions.
ReLU Activation
non-saturating non-linearity
While training with Gradient
Descent these are faster than
saturating non-linearities like
sigmoid and tanh functions.
Convolutional Neural Networks
• Replicated feature approach
• Local Connectivity:
Receptive fields(RFs)
• Shared Weights:
Apply filter to image.
• Pooling:
subsampling layers
Convolutional Neural Networks
One or more convolutional layer
Followed by one or more fully connected layer
Resulting in easy to train networks with many fewer
parameters.
Convolution Layers
Pooling Layer
Convolution Layer
Basic Architecture
Learning a Classifier
Gradient Descent Algorithm
 Calculate Cost Function or Lost Function J(s)
 Calculate Gradient 𝜕𝐽(w)/𝜕w
 Update Weights
Stochastic Gradient Descent: Updates Adjust after example.
Mini-batch SGD: Updates after batches.
We do not use Squared Error measure for training instead we use Softmax
Function for output
Right cost function is Negative Log Likelihood.
Learning a Classifier- Negative Log
likelihood
𝑁𝐿𝐿 𝜃, 𝒟 = −
𝑖=0
|𝒟|
log 𝑃(𝑌 = 𝑦(𝑖)|𝑥 𝑖 , 𝜃)
Where 𝒟 is Dataset
𝜃 is weight parameter
(𝑥 𝑖
, 𝑦 𝑖
) is ith training data. Y is target data.
Overfitting
When the number of training
examples are small and the
architecture is deep, the network
performs well on training data but
worse on test data. i.e. it overfits.
Overfitting Mitigation
Data Augmentation :
Artificially creating more data samples from existing data through various
transformation of images (i.e. rotation, reflection, skewing etc.) and/or dividing
images into small patches and averaging all their predictions.
Applying PCA to the training examples to find out principal components which
correspond to intensity and color of the illumination. Creating artificial data by
adding randomly scaled eigen vectors to the training examples.
𝐼𝑥𝑦𝑅, 𝐼𝑥𝑦𝐺, 𝐼𝑥𝑦𝐵 𝑇 = 𝒑𝟏, 𝒑𝟐, 𝒑𝟑 [𝛼1𝜆1, 𝛼2𝜆2, 𝛼3𝜆3]𝑇
Dropout:
Dropout
Technique to reduce overfitting
Dropout prevents complex co-adaptation on the
training data.
Randomly omit each hidden unit with probability
0.5 and
Its like randomly sampling from 2^H
Architectures, H is number of units in a hidden
layer
Efficient way to average many larger neural nets
ImageNet classification with Deep CNN
Improvement increases with larger datasets
Need model with large learning capacity
CNN’s capacity can be controlled with depth and breadth
Best results in ILSVRC-2010, 2012
CNN Architecture Design
5 Convolution Layers
3 Full Connection Layers
Last output is 1000 way
Training on Multiple GPUs
Current GPU more suited to cross-GPU Parallelization
Putting half of neurons on each GPUs and allowing them to communicate only in
certain layers
Choosing the connectivity is done by cross validation
Local Response Normalization
Activity of neuron i at position (x, y) is normalized to simulate lateral inhibition
inspired by real neurons.
Datasets
ILSVRC started as part of Pascal Visual Object challenge on 2010
1.2 Million training images, 50K validation Images and 150K testing images.
ILSVRC uses 1000 Images for each of 1000 categories.
Two error measures top-1 error, top-5 error.
Top-5 error fraction of test images for which correct label is not among the best 5
results predicted from the model.
Visualization of Learned feature
Tools used for overfitting
Data Augmentation
Dropout
Results
References
[1] A. Krizhevsky, I. Sutskever and G. E. Hinton, "ImageNet Classification with Deep Convolutional Neural
Networks," 2012.
[2] S. Tara, Brian Kingsbury, A.-r. Mohamed and B. Ramabhadran, "Learning Filter Banks within a Deep Neural
Network Framework," in IEEE, 2013.
[3] A. Graves, A.-r. Mohamed and G. Hinton, "Speech Recognition with Deep Recurrent Neural Networks,"
University of Toronto.
[4] A. Graves, "Generating Sequences with Recurrent Neural Networks," arXiv, 2014.
[5] Q. V. Oriol Vinyals, "A Neural Conversational Model," arXiv, 2015.
[6] R. Grishick, J. Donahue, T. Darrel and J. Mallik, "Rich Features Hierarchies for accurate object detection and
semantic segmentation.," UC Berkeley.
[7] A. Karpathy, "CS231n Convolutional Neural Networks for Visual Recognition," Stanford University, [Online].
Available: http://cs231n.github.io/convolutional-networks/.
[8] I. Sutskever, "Training Recurrent Neural Networks," University of Toronto, 2013.
[9] "Convolutional Neural Networks (LeNet)," [Online]. Available: http://deeplearning.net/tutorial/lenet.html.
[10] C. Eugenio, A. Dundar, J. Jin and J. Bates, "An Analysis of the Connections Between Layers of Deep Neural
Networks," arXiv, 2013.
References
[11] M. D. Zeiler and F. Rob, "Visualizing and Understanding Convolutional Networks," arXiv, 2013.
[12] G. Hinton, N. Srivastava, A. Karpathy, I. Sutskever and R. Salakhutdinov, Improving Neural Networks
by preventing co-adaptation of feature detectors, Totonto: arXiv, 2012.
[13] L. Fie-Fie. and A. Karpathy, "Deep Visual Alignment for Generating Image Descriptions,"
Standford University, 2014.
[14] O. Vinyals, A. Toshev., S. Bengio and D. Erthan, "Show and Tell: A Neural Image Caption
Generator.," Google Inc., 2014.
[15] J. M. G. H. IIya Sutskever, "Generating Text with Recurrent Neural Networks," in 28th International
Conference on Machine Learning, Bellevue, 2011.
[16] "Theano," [Online]. Available: http://deeplearning.net/software/theano/index.html. [Accessed 27
10 2015].
[17] "What is GPU Computing ?," NVIDIA, [Online]. Available: http://www.nvidia.com/object/what-is-
gpu-computing.html. [Accessed 27 12 2015].
[18] "GeForce 820M|Specifications," NVIDIA, [Online]. Available:
http://www.geforce.com/hardware/notebook-gpus/geforce-820m/specifications. [Accessed 28
10 2015].

More Related Content

Similar to imageclassification-160206090009.pdf

Scene recognition using Convolutional Neural Network
Scene recognition using Convolutional Neural NetworkScene recognition using Convolutional Neural Network
Scene recognition using Convolutional Neural Network
DhirajGidde
 
Image Captioning Generator using Deep Machine Learning
Image Captioning Generator using Deep Machine LearningImage Captioning Generator using Deep Machine Learning
Image Captioning Generator using Deep Machine Learning
ijtsrd
 
238 243
238 243238 243
238 243
238 243238 243
Devanagari Digit and Character Recognition Using Convolutional Neural Network
Devanagari Digit and Character Recognition Using Convolutional Neural NetworkDevanagari Digit and Character Recognition Using Convolutional Neural Network
Devanagari Digit and Character Recognition Using Convolutional Neural Network
IRJET Journal
 
X trepan an extended trepan for
X trepan an extended trepan forX trepan an extended trepan for
X trepan an extended trepan for
ijaia
 
Targeted Visual Content Recognition Using Multi-Layer Perceptron Neural Network
Targeted Visual Content Recognition Using Multi-Layer Perceptron Neural NetworkTargeted Visual Content Recognition Using Multi-Layer Perceptron Neural Network
Targeted Visual Content Recognition Using Multi-Layer Perceptron Neural Network
ijceronline
 
Plant Disease Detection.pptx
Plant Disease Detection.pptxPlant Disease Detection.pptx
Plant Disease Detection.pptx
vikasmittal92
 
Course Title CS591-Advance Artificial Intelligence
Course Title CS591-Advance Artificial Intelligence           Course Title CS591-Advance Artificial Intelligence
Course Title CS591-Advance Artificial Intelligence
CruzIbarra161
 
Image Segmentation and Classification using Neural Network
Image Segmentation and Classification using Neural NetworkImage Segmentation and Classification using Neural Network
Image Segmentation and Classification using Neural Network
AIRCC Publishing Corporation
 
Image Segmentation and Classification using Neural Network
Image Segmentation and Classification using Neural NetworkImage Segmentation and Classification using Neural Network
Image Segmentation and Classification using Neural Network
AIRCC Publishing Corporation
 
Deep Learning: concepts and use cases (October 2018)
Deep Learning: concepts and use cases (October 2018)Deep Learning: concepts and use cases (October 2018)
Deep Learning: concepts and use cases (October 2018)
Julien SIMON
 
最近の研究情勢についていくために - Deep Learningを中心に -
最近の研究情勢についていくために - Deep Learningを中心に - 最近の研究情勢についていくために - Deep Learningを中心に -
最近の研究情勢についていくために - Deep Learningを中心に -
Hiroshi Fukui
 
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
 
CCS355 Neural Networks & Deep Learning Unit 1 PDF notes with Question bank .pdf
CCS355 Neural Networks & Deep Learning Unit 1 PDF notes with Question bank .pdfCCS355 Neural Networks & Deep Learning Unit 1 PDF notes with Question bank .pdf
CCS355 Neural Networks & Deep Learning Unit 1 PDF notes with Question bank .pdf
Asst.prof M.Gokilavani
 
ImageNet Classification with Deep Convolutional Neural Networks
ImageNet Classification with Deep Convolutional Neural NetworksImageNet Classification with Deep Convolutional Neural Networks
ImageNet Classification with Deep Convolutional Neural Networks
Willy Marroquin (WillyDevNET)
 
IRJET- Machine Learning based Object Identification System using Python
IRJET- Machine Learning based Object Identification System using PythonIRJET- Machine Learning based Object Identification System using Python
IRJET- Machine Learning based Object Identification System using Python
IRJET Journal
 
Comparison Between Levenberg-Marquardt And Scaled Conjugate Gradient Training...
Comparison Between Levenberg-Marquardt And Scaled Conjugate Gradient Training...Comparison Between Levenberg-Marquardt And Scaled Conjugate Gradient Training...
Comparison Between Levenberg-Marquardt And Scaled Conjugate Gradient Training...
CSCJournals
 
Mnist report ppt
Mnist report pptMnist report ppt
Mnist report ppt
RaghunandanJairam
 
IMAGE CLASSIFICATION USING DIFFERENT CLASSICAL APPROACHES
IMAGE CLASSIFICATION USING DIFFERENT CLASSICAL APPROACHESIMAGE CLASSIFICATION USING DIFFERENT CLASSICAL APPROACHES
IMAGE CLASSIFICATION USING DIFFERENT CLASSICAL APPROACHES
Vikash Kumar
 

Similar to imageclassification-160206090009.pdf (20)

Scene recognition using Convolutional Neural Network
Scene recognition using Convolutional Neural NetworkScene recognition using Convolutional Neural Network
Scene recognition using Convolutional Neural Network
 
Image Captioning Generator using Deep Machine Learning
Image Captioning Generator using Deep Machine LearningImage Captioning Generator using Deep Machine Learning
Image Captioning Generator using Deep Machine Learning
 
238 243
238 243238 243
238 243
 
238 243
238 243238 243
238 243
 
Devanagari Digit and Character Recognition Using Convolutional Neural Network
Devanagari Digit and Character Recognition Using Convolutional Neural NetworkDevanagari Digit and Character Recognition Using Convolutional Neural Network
Devanagari Digit and Character Recognition Using Convolutional Neural Network
 
X trepan an extended trepan for
X trepan an extended trepan forX trepan an extended trepan for
X trepan an extended trepan for
 
Targeted Visual Content Recognition Using Multi-Layer Perceptron Neural Network
Targeted Visual Content Recognition Using Multi-Layer Perceptron Neural NetworkTargeted Visual Content Recognition Using Multi-Layer Perceptron Neural Network
Targeted Visual Content Recognition Using Multi-Layer Perceptron Neural Network
 
Plant Disease Detection.pptx
Plant Disease Detection.pptxPlant Disease Detection.pptx
Plant Disease Detection.pptx
 
Course Title CS591-Advance Artificial Intelligence
Course Title CS591-Advance Artificial Intelligence           Course Title CS591-Advance Artificial Intelligence
Course Title CS591-Advance Artificial Intelligence
 
Image Segmentation and Classification using Neural Network
Image Segmentation and Classification using Neural NetworkImage Segmentation and Classification using Neural Network
Image Segmentation and Classification using Neural Network
 
Image Segmentation and Classification using Neural Network
Image Segmentation and Classification using Neural NetworkImage Segmentation and Classification using Neural Network
Image Segmentation and Classification using Neural Network
 
Deep Learning: concepts and use cases (October 2018)
Deep Learning: concepts and use cases (October 2018)Deep Learning: concepts and use cases (October 2018)
Deep Learning: concepts and use cases (October 2018)
 
最近の研究情勢についていくために - Deep Learningを中心に -
最近の研究情勢についていくために - Deep Learningを中心に - 最近の研究情勢についていくために - Deep Learningを中心に -
最近の研究情勢についていくために - Deep Learningを中心に -
 
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)
 
CCS355 Neural Networks & Deep Learning Unit 1 PDF notes with Question bank .pdf
CCS355 Neural Networks & Deep Learning Unit 1 PDF notes with Question bank .pdfCCS355 Neural Networks & Deep Learning Unit 1 PDF notes with Question bank .pdf
CCS355 Neural Networks & Deep Learning Unit 1 PDF notes with Question bank .pdf
 
ImageNet Classification with Deep Convolutional Neural Networks
ImageNet Classification with Deep Convolutional Neural NetworksImageNet Classification with Deep Convolutional Neural Networks
ImageNet Classification with Deep Convolutional Neural Networks
 
IRJET- Machine Learning based Object Identification System using Python
IRJET- Machine Learning based Object Identification System using PythonIRJET- Machine Learning based Object Identification System using Python
IRJET- Machine Learning based Object Identification System using Python
 
Comparison Between Levenberg-Marquardt And Scaled Conjugate Gradient Training...
Comparison Between Levenberg-Marquardt And Scaled Conjugate Gradient Training...Comparison Between Levenberg-Marquardt And Scaled Conjugate Gradient Training...
Comparison Between Levenberg-Marquardt And Scaled Conjugate Gradient Training...
 
Mnist report ppt
Mnist report pptMnist report ppt
Mnist report ppt
 
IMAGE CLASSIFICATION USING DIFFERENT CLASSICAL APPROACHES
IMAGE CLASSIFICATION USING DIFFERENT CLASSICAL APPROACHESIMAGE CLASSIFICATION USING DIFFERENT CLASSICAL APPROACHES
IMAGE CLASSIFICATION USING DIFFERENT CLASSICAL APPROACHES
 

Recently uploaded

2008 BUILDING CONSTRUCTION Illustrated - Ching Chapter 02 The Building.pdf
2008 BUILDING CONSTRUCTION Illustrated - Ching Chapter 02 The Building.pdf2008 BUILDING CONSTRUCTION Illustrated - Ching Chapter 02 The Building.pdf
2008 BUILDING CONSTRUCTION Illustrated - Ching Chapter 02 The Building.pdf
Yasser Mahgoub
 
Properties Railway Sleepers and Test.pptx
Properties Railway Sleepers and Test.pptxProperties Railway Sleepers and Test.pptx
Properties Railway Sleepers and Test.pptx
MDSABBIROJJAMANPAYEL
 
Data Control Language.pptx Data Control Language.pptx
Data Control Language.pptx Data Control Language.pptxData Control Language.pptx Data Control Language.pptx
Data Control Language.pptx Data Control Language.pptx
ramrag33
 
4. Mosca vol I -Fisica-Tipler-5ta-Edicion-Vol-1.pdf
4. Mosca vol I -Fisica-Tipler-5ta-Edicion-Vol-1.pdf4. Mosca vol I -Fisica-Tipler-5ta-Edicion-Vol-1.pdf
4. Mosca vol I -Fisica-Tipler-5ta-Edicion-Vol-1.pdf
Gino153088
 
Rainfall intensity duration frequency curve statistical analysis and modeling...
Rainfall intensity duration frequency curve statistical analysis and modeling...Rainfall intensity duration frequency curve statistical analysis and modeling...
Rainfall intensity duration frequency curve statistical analysis and modeling...
bijceesjournal
 
artificial intelligence and data science contents.pptx
artificial intelligence and data science contents.pptxartificial intelligence and data science contents.pptx
artificial intelligence and data science contents.pptx
GauravCar
 
132/33KV substation case study Presentation
132/33KV substation case study Presentation132/33KV substation case study Presentation
132/33KV substation case study Presentation
kandramariana6
 
cnn.pptx Convolutional neural network used for image classication
cnn.pptx Convolutional neural network used for image classicationcnn.pptx Convolutional neural network used for image classication
cnn.pptx Convolutional neural network used for image classication
SakkaravarthiShanmug
 
Software Quality Assurance-se412-v11.ppt
Software Quality Assurance-se412-v11.pptSoftware Quality Assurance-se412-v11.ppt
Software Quality Assurance-se412-v11.ppt
TaghreedAltamimi
 
Use PyCharm for remote debugging of WSL on a Windo cf5c162d672e4e58b4dde5d797...
Use PyCharm for remote debugging of WSL on a Windo cf5c162d672e4e58b4dde5d797...Use PyCharm for remote debugging of WSL on a Windo cf5c162d672e4e58b4dde5d797...
Use PyCharm for remote debugging of WSL on a Windo cf5c162d672e4e58b4dde5d797...
shadow0702a
 
一比一原版(CalArts毕业证)加利福尼亚艺术学院毕业证如何办理
一比一原版(CalArts毕业证)加利福尼亚艺术学院毕业证如何办理一比一原版(CalArts毕业证)加利福尼亚艺术学院毕业证如何办理
一比一原版(CalArts毕业证)加利福尼亚艺术学院毕业证如何办理
ecqow
 
Software Engineering and Project Management - Introduction, Modeling Concepts...
Software Engineering and Project Management - Introduction, Modeling Concepts...Software Engineering and Project Management - Introduction, Modeling Concepts...
Software Engineering and Project Management - Introduction, Modeling Concepts...
Prakhyath Rai
 
Certificates - Mahmoud Mohamed Moursi Ahmed
Certificates - Mahmoud Mohamed Moursi AhmedCertificates - Mahmoud Mohamed Moursi Ahmed
Certificates - Mahmoud Mohamed Moursi Ahmed
Mahmoud Morsy
 
Engineering Drawings Lecture Detail Drawings 2014.pdf
Engineering Drawings Lecture Detail Drawings 2014.pdfEngineering Drawings Lecture Detail Drawings 2014.pdf
Engineering Drawings Lecture Detail Drawings 2014.pdf
abbyasa1014
 
Embedded machine learning-based road conditions and driving behavior monitoring
Embedded machine learning-based road conditions and driving behavior monitoringEmbedded machine learning-based road conditions and driving behavior monitoring
Embedded machine learning-based road conditions and driving behavior monitoring
IJECEIAES
 
Unit-III-ELECTROCHEMICAL STORAGE DEVICES.ppt
Unit-III-ELECTROCHEMICAL STORAGE DEVICES.pptUnit-III-ELECTROCHEMICAL STORAGE DEVICES.ppt
Unit-III-ELECTROCHEMICAL STORAGE DEVICES.ppt
KrishnaveniKrishnara1
 
AI assisted telemedicine KIOSK for Rural India.pptx
AI assisted telemedicine KIOSK for Rural India.pptxAI assisted telemedicine KIOSK for Rural India.pptx
AI assisted telemedicine KIOSK for Rural India.pptx
architagupta876
 
Welding Metallurgy Ferrous Materials.pdf
Welding Metallurgy Ferrous Materials.pdfWelding Metallurgy Ferrous Materials.pdf
Welding Metallurgy Ferrous Materials.pdf
AjmalKhan50578
 
Advanced control scheme of doubly fed induction generator for wind turbine us...
Advanced control scheme of doubly fed induction generator for wind turbine us...Advanced control scheme of doubly fed induction generator for wind turbine us...
Advanced control scheme of doubly fed induction generator for wind turbine us...
IJECEIAES
 
学校原版美国波士顿大学毕业证学历学位证书原版一模一样
学校原版美国波士顿大学毕业证学历学位证书原版一模一样学校原版美国波士顿大学毕业证学历学位证书原版一模一样
学校原版美国波士顿大学毕业证学历学位证书原版一模一样
171ticu
 

Recently uploaded (20)

2008 BUILDING CONSTRUCTION Illustrated - Ching Chapter 02 The Building.pdf
2008 BUILDING CONSTRUCTION Illustrated - Ching Chapter 02 The Building.pdf2008 BUILDING CONSTRUCTION Illustrated - Ching Chapter 02 The Building.pdf
2008 BUILDING CONSTRUCTION Illustrated - Ching Chapter 02 The Building.pdf
 
Properties Railway Sleepers and Test.pptx
Properties Railway Sleepers and Test.pptxProperties Railway Sleepers and Test.pptx
Properties Railway Sleepers and Test.pptx
 
Data Control Language.pptx Data Control Language.pptx
Data Control Language.pptx Data Control Language.pptxData Control Language.pptx Data Control Language.pptx
Data Control Language.pptx Data Control Language.pptx
 
4. Mosca vol I -Fisica-Tipler-5ta-Edicion-Vol-1.pdf
4. Mosca vol I -Fisica-Tipler-5ta-Edicion-Vol-1.pdf4. Mosca vol I -Fisica-Tipler-5ta-Edicion-Vol-1.pdf
4. Mosca vol I -Fisica-Tipler-5ta-Edicion-Vol-1.pdf
 
Rainfall intensity duration frequency curve statistical analysis and modeling...
Rainfall intensity duration frequency curve statistical analysis and modeling...Rainfall intensity duration frequency curve statistical analysis and modeling...
Rainfall intensity duration frequency curve statistical analysis and modeling...
 
artificial intelligence and data science contents.pptx
artificial intelligence and data science contents.pptxartificial intelligence and data science contents.pptx
artificial intelligence and data science contents.pptx
 
132/33KV substation case study Presentation
132/33KV substation case study Presentation132/33KV substation case study Presentation
132/33KV substation case study Presentation
 
cnn.pptx Convolutional neural network used for image classication
cnn.pptx Convolutional neural network used for image classicationcnn.pptx Convolutional neural network used for image classication
cnn.pptx Convolutional neural network used for image classication
 
Software Quality Assurance-se412-v11.ppt
Software Quality Assurance-se412-v11.pptSoftware Quality Assurance-se412-v11.ppt
Software Quality Assurance-se412-v11.ppt
 
Use PyCharm for remote debugging of WSL on a Windo cf5c162d672e4e58b4dde5d797...
Use PyCharm for remote debugging of WSL on a Windo cf5c162d672e4e58b4dde5d797...Use PyCharm for remote debugging of WSL on a Windo cf5c162d672e4e58b4dde5d797...
Use PyCharm for remote debugging of WSL on a Windo cf5c162d672e4e58b4dde5d797...
 
一比一原版(CalArts毕业证)加利福尼亚艺术学院毕业证如何办理
一比一原版(CalArts毕业证)加利福尼亚艺术学院毕业证如何办理一比一原版(CalArts毕业证)加利福尼亚艺术学院毕业证如何办理
一比一原版(CalArts毕业证)加利福尼亚艺术学院毕业证如何办理
 
Software Engineering and Project Management - Introduction, Modeling Concepts...
Software Engineering and Project Management - Introduction, Modeling Concepts...Software Engineering and Project Management - Introduction, Modeling Concepts...
Software Engineering and Project Management - Introduction, Modeling Concepts...
 
Certificates - Mahmoud Mohamed Moursi Ahmed
Certificates - Mahmoud Mohamed Moursi AhmedCertificates - Mahmoud Mohamed Moursi Ahmed
Certificates - Mahmoud Mohamed Moursi Ahmed
 
Engineering Drawings Lecture Detail Drawings 2014.pdf
Engineering Drawings Lecture Detail Drawings 2014.pdfEngineering Drawings Lecture Detail Drawings 2014.pdf
Engineering Drawings Lecture Detail Drawings 2014.pdf
 
Embedded machine learning-based road conditions and driving behavior monitoring
Embedded machine learning-based road conditions and driving behavior monitoringEmbedded machine learning-based road conditions and driving behavior monitoring
Embedded machine learning-based road conditions and driving behavior monitoring
 
Unit-III-ELECTROCHEMICAL STORAGE DEVICES.ppt
Unit-III-ELECTROCHEMICAL STORAGE DEVICES.pptUnit-III-ELECTROCHEMICAL STORAGE DEVICES.ppt
Unit-III-ELECTROCHEMICAL STORAGE DEVICES.ppt
 
AI assisted telemedicine KIOSK for Rural India.pptx
AI assisted telemedicine KIOSK for Rural India.pptxAI assisted telemedicine KIOSK for Rural India.pptx
AI assisted telemedicine KIOSK for Rural India.pptx
 
Welding Metallurgy Ferrous Materials.pdf
Welding Metallurgy Ferrous Materials.pdfWelding Metallurgy Ferrous Materials.pdf
Welding Metallurgy Ferrous Materials.pdf
 
Advanced control scheme of doubly fed induction generator for wind turbine us...
Advanced control scheme of doubly fed induction generator for wind turbine us...Advanced control scheme of doubly fed induction generator for wind turbine us...
Advanced control scheme of doubly fed induction generator for wind turbine us...
 
学校原版美国波士顿大学毕业证学历学位证书原版一模一样
学校原版美国波士顿大学毕业证学历学位证书原版一模一样学校原版美国波士顿大学毕业证学历学位证书原版一模一样
学校原版美国波士顿大学毕业证学历学位证书原版一模一样
 

imageclassification-160206090009.pdf

  • 1. Image Classification with Deep Neural Networks Yogendra Tamang Sabin Devkota Presented By: February 6, 2016 ImageNet Classification with Deep Convolutional Neural Networks A. Krizhevsky, I. Sutskever, G. Hinton #pwlnepal PWL Kathmandu Papers We Love Kathmandu
  • 2. Outline Background Image Classification Activation Functions Convolution Neural Networks Other Issues Techniques used in other papers And So on…
  • 3. Background Learning Supervised Unsupervised AI Tasks Classification and Regression Clustering Machine Learning Problem Supervised Regression Classfication Unsupervised Clustering
  • 4. Background Classification  Classifies data into one of discrete classes  Eg. Classifying digits  Cost Function for Classification Task may be Logistic Regression or Log-likelihood Regression  Predicts continuous real valued output  Eg. Stock Price Predictions  Cost function for regression type problem are MSE(Mean Squared Error)
  • 5. Introduction • Input Image is array of number for computer • Assign a label to input image from set of categories • One of core problems in computer vision
  • 6. Neural Networks and Multilayer Perceptrons
  • 7. Neural Networks and Multi Layer Perceptrons “activation” of unit in layer matrix of weights controlling function mapping from layer to layer They use Activation Functions.
  • 8. ReLU Activation non-saturating non-linearity While training with Gradient Descent these are faster than saturating non-linearities like sigmoid and tanh functions.
  • 9. Convolutional Neural Networks • Replicated feature approach • Local Connectivity: Receptive fields(RFs) • Shared Weights: Apply filter to image. • Pooling: subsampling layers
  • 10. Convolutional Neural Networks One or more convolutional layer Followed by one or more fully connected layer Resulting in easy to train networks with many fewer parameters.
  • 15. Learning a Classifier Gradient Descent Algorithm  Calculate Cost Function or Lost Function J(s)  Calculate Gradient 𝜕𝐽(w)/𝜕w  Update Weights Stochastic Gradient Descent: Updates Adjust after example. Mini-batch SGD: Updates after batches. We do not use Squared Error measure for training instead we use Softmax Function for output Right cost function is Negative Log Likelihood.
  • 16. Learning a Classifier- Negative Log likelihood 𝑁𝐿𝐿 𝜃, 𝒟 = − 𝑖=0 |𝒟| log 𝑃(𝑌 = 𝑦(𝑖)|𝑥 𝑖 , 𝜃) Where 𝒟 is Dataset 𝜃 is weight parameter (𝑥 𝑖 , 𝑦 𝑖 ) is ith training data. Y is target data.
  • 17. Overfitting When the number of training examples are small and the architecture is deep, the network performs well on training data but worse on test data. i.e. it overfits.
  • 18. Overfitting Mitigation Data Augmentation : Artificially creating more data samples from existing data through various transformation of images (i.e. rotation, reflection, skewing etc.) and/or dividing images into small patches and averaging all their predictions. Applying PCA to the training examples to find out principal components which correspond to intensity and color of the illumination. Creating artificial data by adding randomly scaled eigen vectors to the training examples. 𝐼𝑥𝑦𝑅, 𝐼𝑥𝑦𝐺, 𝐼𝑥𝑦𝐵 𝑇 = 𝒑𝟏, 𝒑𝟐, 𝒑𝟑 [𝛼1𝜆1, 𝛼2𝜆2, 𝛼3𝜆3]𝑇 Dropout:
  • 19. Dropout Technique to reduce overfitting Dropout prevents complex co-adaptation on the training data. Randomly omit each hidden unit with probability 0.5 and Its like randomly sampling from 2^H Architectures, H is number of units in a hidden layer Efficient way to average many larger neural nets
  • 20. ImageNet classification with Deep CNN Improvement increases with larger datasets Need model with large learning capacity CNN’s capacity can be controlled with depth and breadth Best results in ILSVRC-2010, 2012
  • 21. CNN Architecture Design 5 Convolution Layers 3 Full Connection Layers Last output is 1000 way
  • 22. Training on Multiple GPUs Current GPU more suited to cross-GPU Parallelization Putting half of neurons on each GPUs and allowing them to communicate only in certain layers Choosing the connectivity is done by cross validation
  • 23. Local Response Normalization Activity of neuron i at position (x, y) is normalized to simulate lateral inhibition inspired by real neurons.
  • 24. Datasets ILSVRC started as part of Pascal Visual Object challenge on 2010 1.2 Million training images, 50K validation Images and 150K testing images. ILSVRC uses 1000 Images for each of 1000 categories. Two error measures top-1 error, top-5 error. Top-5 error fraction of test images for which correct label is not among the best 5 results predicted from the model.
  • 26. Tools used for overfitting Data Augmentation Dropout
  • 28. References [1] A. Krizhevsky, I. Sutskever and G. E. Hinton, "ImageNet Classification with Deep Convolutional Neural Networks," 2012. [2] S. Tara, Brian Kingsbury, A.-r. Mohamed and B. Ramabhadran, "Learning Filter Banks within a Deep Neural Network Framework," in IEEE, 2013. [3] A. Graves, A.-r. Mohamed and G. Hinton, "Speech Recognition with Deep Recurrent Neural Networks," University of Toronto. [4] A. Graves, "Generating Sequences with Recurrent Neural Networks," arXiv, 2014. [5] Q. V. Oriol Vinyals, "A Neural Conversational Model," arXiv, 2015. [6] R. Grishick, J. Donahue, T. Darrel and J. Mallik, "Rich Features Hierarchies for accurate object detection and semantic segmentation.," UC Berkeley. [7] A. Karpathy, "CS231n Convolutional Neural Networks for Visual Recognition," Stanford University, [Online]. Available: http://cs231n.github.io/convolutional-networks/. [8] I. Sutskever, "Training Recurrent Neural Networks," University of Toronto, 2013. [9] "Convolutional Neural Networks (LeNet)," [Online]. Available: http://deeplearning.net/tutorial/lenet.html. [10] C. Eugenio, A. Dundar, J. Jin and J. Bates, "An Analysis of the Connections Between Layers of Deep Neural Networks," arXiv, 2013.
  • 29. References [11] M. D. Zeiler and F. Rob, "Visualizing and Understanding Convolutional Networks," arXiv, 2013. [12] G. Hinton, N. Srivastava, A. Karpathy, I. Sutskever and R. Salakhutdinov, Improving Neural Networks by preventing co-adaptation of feature detectors, Totonto: arXiv, 2012. [13] L. Fie-Fie. and A. Karpathy, "Deep Visual Alignment for Generating Image Descriptions," Standford University, 2014. [14] O. Vinyals, A. Toshev., S. Bengio and D. Erthan, "Show and Tell: A Neural Image Caption Generator.," Google Inc., 2014. [15] J. M. G. H. IIya Sutskever, "Generating Text with Recurrent Neural Networks," in 28th International Conference on Machine Learning, Bellevue, 2011. [16] "Theano," [Online]. Available: http://deeplearning.net/software/theano/index.html. [Accessed 27 10 2015]. [17] "What is GPU Computing ?," NVIDIA, [Online]. Available: http://www.nvidia.com/object/what-is- gpu-computing.html. [Accessed 27 12 2015]. [18] "GeForce 820M|Specifications," NVIDIA, [Online]. Available: http://www.geforce.com/hardware/notebook-gpus/geforce-820m/specifications. [Accessed 28 10 2015].