SlideShare une entreprise Scribd logo
1  sur  68
Télécharger pour lire hors ligne
Deep Learning (2)
Convolutional Neural Networks
PRESENTED BY HENGYANG (TROY) LU
APRIL 22ND, 2017
Outlines for Today
Section I. Basics of Convolutional Neural Networks
◦ What is CNN?
◦ Comparison with traditional Neural Networks
◦ Why we need CNNs?
◦ Boosting Technologies for CNNs
Section II. More Details of Convolutional Neural Networks
◦ AlexNet  A Network for classification  The “Equation”
◦ Optimization Methods in Neural Networks  The Numerical “Solver”
Section III. Convolutional Neural Networks with Tensorflow and TFlearn
Section I. The Basics
Image from http://parse.ele.tue.nl/cluster/2/CNNArchitecture.jpg
What is Convolutional Neural Network?
What is convolution?
◦ It is a specialized linear operation.
◦ A 2D convolution is shown on the right. (Images From: community.arm.com)
◦ Strictly speaking, it’s cross-correlation.
◦ In CNNs, all convolution operations are actually cross-correlation.
Convolutional neural networks are neural networks that use convolution in place of general
matrix multiplication in at least one of their layers. They are very powerful in processing data
with grid-like topology. [1]
[1] Ian Goodfellow, Yoshua Bengio, Aaron Courville , Deep Learning
Comparison with MLP
In last lecture, we got to know MLP(multi-layer perceptron), where the operation from one
layer to neurons in the upper layer is matrix multiplication controlled by weights and bias.
In CNNs, where do those “Neurons” go?
◦ Each neuron is one element in the matrix after convolution
◦ weights are shared
Comparison with MLP
 Local Connections
A
B
C
A, with convolution kernel size = 3, the activated neurons are only affected by local neurons , unlike in B,
where there are full connections; however, with depth, the receptive field can expand, and get global connections
to neurons in lower layer.
Why we Need Convolutional Neural
Networks?
A lot of challenges we could not deal with in the past, now with CNN, yes, we can! :D
A lot of things we could do in the past, now with CNN, we can do better!
CNNs represent current state-of-the-art technique in classification, object detection etc.
Now, let’s take a brief look at these achievements…
MNIST Hand-written digits recognition
The MNIST database of handwritten digits
◦ Has a training set of 60000 examples,
◦ Has a test set of 10000 examples,
◦ Is a subset of a larger set available from NIST ( National Institute of Standards and Technology)
◦ The digits have been size-normalized (28x28) and centered in a fixed-size image.
http://simonwinder.com/2015/07/training-neural-nets-on-mnist-digits/
MNIST Classification Record [1]
Classifier Preprocessing Best Test Error Rate (%)
Linear Classifiers deskewing 7.6
K-Nearest Neighbours Shape-context feature extraction 0.63
Boosted Stumps Haar features 0.87
Non-linear classifiers none 3.3
SVMs deskewing 0.56
Neural Nets none 0.35
Convolution Neural Nets Width normalization 0.23
[1] http://yann.lecun.com/exdb/mnist/
The ImageNet Challenge [1][2]
The ImageNet Large Scale Visual Recognition Challenge (ILSVRC) is a benchmark in object
category classification and detection on hundreds of object categories and millions of images
◦ The ILSVRC challenge has been running annually since 2010, following the footsteps of PASCAL VOC
challenge, which was established in 2005.
◦ ILSVRC 2010, 1,461406 images and 1000 object classes.
◦ Images are annotated, and annotations fall into one of two categories
◦ (1) image-level annotation of a binary label for the presence or absence of an object class in the image;
◦ (2) object-level annotation of a tight bounding box and class label around an object instance in the image.
◦ ILSVRC 2017, the last ILSVRC challenge.
◦ In these years, several convolutional neural network structure won the first place:
◦ AlexNet 2012
◦ InceptionNet 2014
◦ Deep Residual Network 2015
[1] http://image-net.org/challenges/LSVRC/2017/
[2] Olga Russakovsky et al., ImageNet Large Scale Visual Recognition Challenge
ImageNet : Diversity of Data
ImageNet : Fine-grained classes
ImageNet: Tasks
PRISMA
Technology Behind PRISMA [1]
Deep Convolutional Neural Networks
(a) Separate the content and style of an image
(b) Recombine the content of one image with
the style of another image
[1] Leon A. Gatys et al, A Neural Algorithm of Artistic Style
Boosting Technology for CNNs
The First CNN prototype appeared much earlier, but why it becomes super-hot only in the recent
years?
◦ Huge amount of data and advanced storage/memory systems
◦ GPU acceleration which is super fast in convolution operations (Nvidia GPU Tesla K40 1.4 TFlops)
◦ Deep neural network structures
◦ Optimization methods for training the deep CNNs are invented, like stochastic gradient descent
◦ Off-the-shelf software package solutions are available and easy to use
◦ Progress in both hardware and software make CNNs the ONE!
Section II: More Details [1]
http://www.ritchieng.com/machine-learning/deep-learning/convs/
[1] Slides in section II, credit from slides presented by Tugce Tasci and Kyunghee Kim
AlexNet  Dataset
AlexNet  Dataset
Architecture
Conv L1 Conv L2 Conv L3 Conv L4 Conv L5
Fully
Connected
L6
Fully
Connected
L7
Output
Layer
L8
Layer 1 (Convolutional)
Layer 1 (Convolutional)
ReLU Nonlinearity
ReLU Nonlinearity
Local Response Normalization
Overlapping Pooling
Pooling summarize the outputs of neighbouring groups of neurons in the same kernel map.
Two important parameters
◦ Kernel size : z
◦ Stride size: s
◦ If s < z, then the max-pooling is overlapped
In the experiment, s=2, z=3 overlapped pooling reduces the top-1 and top-5 error rates by 0.4%
and 0.3%, respectively, compared with s=2 and z=2 non-overlapping case.
Reduce Overfitting
Reduce Overfitting
Reduce Overfitting
Reduce Overfitting
Train the CNNs  Optimization
Techniques
Back-propagation
◦ Sparse Connections of CNNs decrease the complexity of Back-Propagation
◦ ReLU activation function relieves the vanishing gradient problem
Stochastic Gradient Descent
Loss Minimization
Slide credit from Nadav Cohen, “Adam: A Method for Stochastic Optimization”
Large-Scale Setting
Slide credit from Nadav Cohen, “Adam: A Method for Stochastic Optimization”
Optimization Methods Requirements
Slide credit from Nadav Cohen, “Adam: A Method for Stochastic Optimization”
Stochastic Gradient Descent (SGD)
Slide credit from Nadav Cohen, “Adam: A Method for Stochastic Optimization”
Variants to the basic SGD
Nestrov’s Accelerated Gradient (SGD)
Adaptive Gradient (AdaGrad)
Root Mean Square Propagation (RMSProp)
Adaptive Moment Estimation (Adam)
NAG
Slide credit from Nadav Cohen, “Adam: A Method for Stochastic Optimization”
AdaGrad
Slide credit from Nadav Cohen, “Adam: A Method for Stochastic Optimization”
RMSProp
Slide credit from Nadav Cohen, “Adam: A Method for Stochastic Optimization”
ADAM
Slide credit from Nadav Cohen, “Adam: A Method for Stochastic Optimization”
ADAM
Slide credit from Nadav Cohen, “Adam: A Method for Stochastic Optimization”
Comparisons of Different Optimization
Methods
Slide credit from Nadav Cohen, “Adam: A Method for Stochastic Optimization”
Multi-Layer Neural Networks on MNIST
Slide credit from Nadav Cohen, “Adam: A Method for Stochastic Optimization”
Convolutional Neural Networks on CIFAR-10
Slide credit from Nadav Cohen, “Adam: A Method for Stochastic Optimization”
SGD for AlexNet
Results: ILSVRC-2010
Results: ILSVRC-2012
Section III. CNNs with Tensorflow and
TFlearn
Images from Peter Goldsborough, A Tour of Tensorflow
Tensorflow
Tensorflow is an open-source library for numerical computation using data flow graphs
◦ Developed by Google Brain Team and Google’s Machine Intelligence research Org.
Implementation ML in tensorflow
◦ In tensorflow, computations are represented using Graphs
◦ Each node is an operation (OP)
◦ Data is represented as Tensors
◦ OP takes Tensors and returns Tensors
Tensorflow Demo Examples, credit from Jesus Fernandez Bes, “Introduction to convolutional Networks using Tensorflow”
Construction of Computational Graph
Follow the 3-steps pattern
◦ 1. inference() – Builds the graph as far as is required for running the network forward to make
predictions
◦ 2. loss() – Adds to the inference graph the ops required to generate loss
◦ 3. training() – Adds to the loss graph the ops required to compute and apply gradients
Tensorflow Demo Examples, credit from Jesus Fernandez Bes, “Introduction to convolutional Networks using Tensorflow”
Deep Convolutional Networks in
Tensorflow
Load the training data, using MNIST
from tensorflow.examples.tutorials.mnist import input_data
Tensorflow Demo Examples, credit from Jesus Fernandez Bes, “Introduction to convolutional Networks using Tensorflow”
Weight Initialization
Tensorflow Demo Examples, credit from Jesus Fernandez Bes, “Introduction to convolutional Networks using Tensorflow”
Convolution and Pooling
Tensorflow Demo Examples, credit from Jesus Fernandez Bes, “Introduction to convolutional Networks using Tensorflow”
First Convolutional Layer
Tensorflow Demo Examples, credit from Jesus Fernandez Bes, “Introduction to convolutional Networks using Tensorflow”
Second Convolutional Layer
Tensorflow Demo Examples, credit from Jesus Fernandez Bes, “Introduction to convolutional Networks using Tensorflow”
Fully Connected Layer
Tensorflow Demo Examples, credit from Jesus Fernandez Bes, “Introduction to convolutional Networks using Tensorflow”
Dropout
Tensorflow Demo Examples, credit from Jesus Fernandez Bes, “Introduction to convolutional Networks using Tensorflow”
Readout Layer
Tensorflow Demo Examples, credit from Jesus Fernandez Bes, “Introduction to convolutional Networks using Tensorflow”
Train and Evaluate
Tensorflow Demo Examples, credit from Jesus Fernandez Bes, “Introduction to convolutional Networks using Tensorflow”
Execute
Tensorflow Demo Examples, credit from Jesus Fernandez Bes, “Introduction to convolutional Networks using Tensorflow”
TFLearn
TFLearn is an abstraction library built on top of Tensorflow that provides high-level building
blocks to quickly construct TensorFlow graphs.
◦ Highly modular interface
◦ Allow rapid chaining of neural network layers, regularization functions, optimizers and other elements
◦ Can be used with tensorflow hybridly
In the following part, let’s implement the previous CNN model with tflearn, and see how much
easier life is now!
TFLearn Website http://tflearn.org/
Redo the same thing with TFLearn
Import the packages
TFLearn Website http://tflearn.org/
Load MNIST dataset
TFLearn Website http://tflearn.org/
Build the convolutional network
TFLearn Website http://tflearn.org/
Training the Network
TFLearn Website http://tflearn.org/
Conclusion
Pros:
◦ Deep Convolutional Neural Networks represent current state-of-the-art techniques in image
classification, object detection and localization
◦ Powerful CNN models are like AlexNet, InceptionNet, Deep Residual Networks
◦ Open-source libraries for deploying applications with CNNs very fast
◦ Convolutional Neural Networks can share pre-trained weights, which is the basis for transfer learning
Cons:
◦ The interpretation and mechanism of CNNs are not clear, we don’t know why they work better than
previous models
◦ Large number of training data and annotations are needed, which may not be practical in some
problems.
Thank You :D

Contenu connexe

Tendances

Convolutional Neural Network (CNN)
Convolutional Neural Network (CNN)Convolutional Neural Network (CNN)
Convolutional Neural Network (CNN)Muhammad Haroon
 
Image classification using cnn
Image classification using cnnImage classification using cnn
Image classification using cnnSumeraHangi
 
Introduction to CNN
Introduction to CNNIntroduction to CNN
Introduction to CNNShuai Zhang
 
What Is Deep Learning? | Introduction to Deep Learning | Deep Learning Tutori...
What Is Deep Learning? | Introduction to Deep Learning | Deep Learning Tutori...What Is Deep Learning? | Introduction to Deep Learning | Deep Learning Tutori...
What Is Deep Learning? | Introduction to Deep Learning | Deep Learning Tutori...Simplilearn
 
Introduction to Recurrent Neural Network
Introduction to Recurrent Neural NetworkIntroduction to Recurrent Neural Network
Introduction to Recurrent Neural NetworkYan Xu
 
Deep Learning - CNN and RNN
Deep Learning - CNN and RNNDeep Learning - CNN and RNN
Deep Learning - CNN and RNNAshray Bhandare
 
Introduction to Deep Learning
Introduction to Deep LearningIntroduction to Deep Learning
Introduction to Deep LearningOswald Campesato
 
Convolution Neural Network (CNN)
Convolution Neural Network (CNN)Convolution Neural Network (CNN)
Convolution Neural Network (CNN)Basit Rafiq
 
Training Neural Networks
Training Neural NetworksTraining Neural Networks
Training Neural NetworksDatabricks
 
Recurrent Neural Networks, LSTM and GRU
Recurrent Neural Networks, LSTM and GRURecurrent Neural Networks, LSTM and GRU
Recurrent Neural Networks, LSTM and GRUananth
 
Introduction to Deep learning
Introduction to Deep learningIntroduction to Deep learning
Introduction to Deep learningleopauly
 
Convolutional neural network
Convolutional neural networkConvolutional neural network
Convolutional neural networkFerdous ahmed
 
Deep Learning - RNN and CNN
Deep Learning - RNN and CNNDeep Learning - RNN and CNN
Deep Learning - RNN and CNNPradnya Saval
 
Image segmentation with deep learning
Image segmentation with deep learningImage segmentation with deep learning
Image segmentation with deep learningAntonio Rueda-Toicen
 
Recurrent Neural Networks. Part 1: Theory
Recurrent Neural Networks. Part 1: TheoryRecurrent Neural Networks. Part 1: Theory
Recurrent Neural Networks. Part 1: TheoryAndrii Gakhov
 
Introduction to Deep Learning, Keras, and TensorFlow
Introduction to Deep Learning, Keras, and TensorFlowIntroduction to Deep Learning, Keras, and TensorFlow
Introduction to Deep Learning, Keras, and TensorFlowSri Ambati
 
Modern Convolutional Neural Network techniques for image segmentation
Modern Convolutional Neural Network techniques for image segmentationModern Convolutional Neural Network techniques for image segmentation
Modern Convolutional Neural Network techniques for image segmentationGioele Ciaparrone
 

Tendances (20)

Convolutional Neural Network (CNN)
Convolutional Neural Network (CNN)Convolutional Neural Network (CNN)
Convolutional Neural Network (CNN)
 
Image classification using cnn
Image classification using cnnImage classification using cnn
Image classification using cnn
 
Introduction to CNN
Introduction to CNNIntroduction to CNN
Introduction to CNN
 
What Is Deep Learning? | Introduction to Deep Learning | Deep Learning Tutori...
What Is Deep Learning? | Introduction to Deep Learning | Deep Learning Tutori...What Is Deep Learning? | Introduction to Deep Learning | Deep Learning Tutori...
What Is Deep Learning? | Introduction to Deep Learning | Deep Learning Tutori...
 
Introduction to Recurrent Neural Network
Introduction to Recurrent Neural NetworkIntroduction to Recurrent Neural Network
Introduction to Recurrent Neural Network
 
Deep Learning - CNN and RNN
Deep Learning - CNN and RNNDeep Learning - CNN and RNN
Deep Learning - CNN and RNN
 
Deep learning
Deep learning Deep learning
Deep learning
 
Introduction to Deep Learning
Introduction to Deep LearningIntroduction to Deep Learning
Introduction to Deep Learning
 
Convolution Neural Network (CNN)
Convolution Neural Network (CNN)Convolution Neural Network (CNN)
Convolution Neural Network (CNN)
 
Cnn
CnnCnn
Cnn
 
Training Neural Networks
Training Neural NetworksTraining Neural Networks
Training Neural Networks
 
CNN Tutorial
CNN TutorialCNN Tutorial
CNN Tutorial
 
Recurrent Neural Networks, LSTM and GRU
Recurrent Neural Networks, LSTM and GRURecurrent Neural Networks, LSTM and GRU
Recurrent Neural Networks, LSTM and GRU
 
Introduction to Deep learning
Introduction to Deep learningIntroduction to Deep learning
Introduction to Deep learning
 
Convolutional neural network
Convolutional neural networkConvolutional neural network
Convolutional neural network
 
Deep Learning - RNN and CNN
Deep Learning - RNN and CNNDeep Learning - RNN and CNN
Deep Learning - RNN and CNN
 
Image segmentation with deep learning
Image segmentation with deep learningImage segmentation with deep learning
Image segmentation with deep learning
 
Recurrent Neural Networks. Part 1: Theory
Recurrent Neural Networks. Part 1: TheoryRecurrent Neural Networks. Part 1: Theory
Recurrent Neural Networks. Part 1: Theory
 
Introduction to Deep Learning, Keras, and TensorFlow
Introduction to Deep Learning, Keras, and TensorFlowIntroduction to Deep Learning, Keras, and TensorFlow
Introduction to Deep Learning, Keras, and TensorFlow
 
Modern Convolutional Neural Network techniques for image segmentation
Modern Convolutional Neural Network techniques for image segmentationModern Convolutional Neural Network techniques for image segmentation
Modern Convolutional Neural Network techniques for image segmentation
 

Similaire à Convolutional neural network

Small Deep-Neural-Networks: Their Advantages and Their Design
Small Deep-Neural-Networks: Their Advantages and Their DesignSmall Deep-Neural-Networks: Their Advantages and Their Design
Small Deep-Neural-Networks: Their Advantages and Their DesignForrest Iandola
 
Saptashwa_Mitra_Sitakanta_Mishra_Final_Project_Report
Saptashwa_Mitra_Sitakanta_Mishra_Final_Project_ReportSaptashwa_Mitra_Sitakanta_Mishra_Final_Project_Report
Saptashwa_Mitra_Sitakanta_Mishra_Final_Project_ReportSitakanta Mishra
 
Towards better analysis of deep convolutional neural networks
Towards better analysis of deep convolutional neural networksTowards better analysis of deep convolutional neural networks
Towards better analysis of deep convolutional neural networks曾 子芸
 
Introduction to computer vision
Introduction to computer visionIntroduction to computer vision
Introduction to computer visionMarcin Jedyk
 
DLD meetup 2017, Efficient Deep Learning
DLD meetup 2017, Efficient Deep LearningDLD meetup 2017, Efficient Deep Learning
DLD meetup 2017, Efficient Deep LearningBrodmann17
 
Introduction to computer vision with Convoluted Neural Networks
Introduction to computer vision with Convoluted Neural NetworksIntroduction to computer vision with Convoluted Neural Networks
Introduction to computer vision with Convoluted Neural NetworksMarcinJedyk
 
Synthetic dialogue generation with Deep Learning
Synthetic dialogue generation with Deep LearningSynthetic dialogue generation with Deep Learning
Synthetic dialogue generation with Deep LearningS N
 
Anomaly Detection with Azure and .NET
Anomaly Detection with Azure and .NETAnomaly Detection with Azure and .NET
Anomaly Detection with Azure and .NETMarco Parenzan
 
Anomaly Detection with Azure and .net
Anomaly Detection with Azure and .netAnomaly Detection with Azure and .net
Anomaly Detection with Azure and .netMarco Parenzan
 
Improving Hardware Efficiency for DNN Applications
Improving Hardware Efficiency for DNN ApplicationsImproving Hardware Efficiency for DNN Applications
Improving Hardware Efficiency for DNN ApplicationsChester Chen
 
MDEC Data Matters Series: machine learning and Deep Learning, A Primer
MDEC Data Matters Series: machine learning and Deep Learning, A PrimerMDEC Data Matters Series: machine learning and Deep Learning, A Primer
MDEC Data Matters Series: machine learning and Deep Learning, A PrimerPoo Kuan Hoong
 
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
 
Architecture Design for Deep Neural Networks I
Architecture Design for Deep Neural Networks IArchitecture Design for Deep Neural Networks I
Architecture Design for Deep Neural Networks IWanjin Yu
 
Transfer Learning and Fine-tuning Deep Neural Networks
 Transfer Learning and Fine-tuning Deep Neural Networks Transfer Learning and Fine-tuning Deep Neural Networks
Transfer Learning and Fine-tuning Deep Neural NetworksPyData
 
(Research Note) Delving deeper into convolutional neural networks for camera ...
(Research Note) Delving deeper into convolutional neural networks for camera ...(Research Note) Delving deeper into convolutional neural networks for camera ...
(Research Note) Delving deeper into convolutional neural networks for camera ...Jacky Liu
 
Convolutional Neural Networks - Xavier Giro - UPC TelecomBCN Barcelona 2020
Convolutional Neural Networks - Xavier Giro - UPC TelecomBCN Barcelona 2020Convolutional Neural Networks - Xavier Giro - UPC TelecomBCN Barcelona 2020
Convolutional Neural Networks - Xavier Giro - UPC TelecomBCN Barcelona 2020Universitat Politècnica de Catalunya
 
Deep-learning-for-computer-vision-applications-using-matlab.pdf
Deep-learning-for-computer-vision-applications-using-matlab.pdfDeep-learning-for-computer-vision-applications-using-matlab.pdf
Deep-learning-for-computer-vision-applications-using-matlab.pdfAubainYro1
 
Convolutional Neural Networks for Image Classification (Cape Town Deep Learni...
Convolutional Neural Networks for Image Classification (Cape Town Deep Learni...Convolutional Neural Networks for Image Classification (Cape Town Deep Learni...
Convolutional Neural Networks for Image Classification (Cape Town Deep Learni...Alex Conway
 
deeplearning
deeplearningdeeplearning
deeplearninghuda2018
 

Similaire à Convolutional neural network (20)

Small Deep-Neural-Networks: Their Advantages and Their Design
Small Deep-Neural-Networks: Their Advantages and Their DesignSmall Deep-Neural-Networks: Their Advantages and Their Design
Small Deep-Neural-Networks: Their Advantages and Their Design
 
Saptashwa_Mitra_Sitakanta_Mishra_Final_Project_Report
Saptashwa_Mitra_Sitakanta_Mishra_Final_Project_ReportSaptashwa_Mitra_Sitakanta_Mishra_Final_Project_Report
Saptashwa_Mitra_Sitakanta_Mishra_Final_Project_Report
 
Towards better analysis of deep convolutional neural networks
Towards better analysis of deep convolutional neural networksTowards better analysis of deep convolutional neural networks
Towards better analysis of deep convolutional neural networks
 
Introduction to computer vision
Introduction to computer visionIntroduction to computer vision
Introduction to computer vision
 
DLD meetup 2017, Efficient Deep Learning
DLD meetup 2017, Efficient Deep LearningDLD meetup 2017, Efficient Deep Learning
DLD meetup 2017, Efficient Deep Learning
 
Introduction to computer vision with Convoluted Neural Networks
Introduction to computer vision with Convoluted Neural NetworksIntroduction to computer vision with Convoluted Neural Networks
Introduction to computer vision with Convoluted Neural Networks
 
Synthetic dialogue generation with Deep Learning
Synthetic dialogue generation with Deep LearningSynthetic dialogue generation with Deep Learning
Synthetic dialogue generation with Deep Learning
 
Introduction to deep learning
Introduction to deep learningIntroduction to deep learning
Introduction to deep learning
 
Anomaly Detection with Azure and .NET
Anomaly Detection with Azure and .NETAnomaly Detection with Azure and .NET
Anomaly Detection with Azure and .NET
 
Anomaly Detection with Azure and .net
Anomaly Detection with Azure and .netAnomaly Detection with Azure and .net
Anomaly Detection with Azure and .net
 
Improving Hardware Efficiency for DNN Applications
Improving Hardware Efficiency for DNN ApplicationsImproving Hardware Efficiency for DNN Applications
Improving Hardware Efficiency for DNN Applications
 
MDEC Data Matters Series: machine learning and Deep Learning, A Primer
MDEC Data Matters Series: machine learning and Deep Learning, A PrimerMDEC Data Matters Series: machine learning and Deep Learning, A Primer
MDEC Data Matters Series: machine learning and Deep Learning, A Primer
 
Cvpr 2018 papers review (efficient computing)
Cvpr 2018 papers review (efficient computing)Cvpr 2018 papers review (efficient computing)
Cvpr 2018 papers review (efficient computing)
 
Architecture Design for Deep Neural Networks I
Architecture Design for Deep Neural Networks IArchitecture Design for Deep Neural Networks I
Architecture Design for Deep Neural Networks I
 
Transfer Learning and Fine-tuning Deep Neural Networks
 Transfer Learning and Fine-tuning Deep Neural Networks Transfer Learning and Fine-tuning Deep Neural Networks
Transfer Learning and Fine-tuning Deep Neural Networks
 
(Research Note) Delving deeper into convolutional neural networks for camera ...
(Research Note) Delving deeper into convolutional neural networks for camera ...(Research Note) Delving deeper into convolutional neural networks for camera ...
(Research Note) Delving deeper into convolutional neural networks for camera ...
 
Convolutional Neural Networks - Xavier Giro - UPC TelecomBCN Barcelona 2020
Convolutional Neural Networks - Xavier Giro - UPC TelecomBCN Barcelona 2020Convolutional Neural Networks - Xavier Giro - UPC TelecomBCN Barcelona 2020
Convolutional Neural Networks - Xavier Giro - UPC TelecomBCN Barcelona 2020
 
Deep-learning-for-computer-vision-applications-using-matlab.pdf
Deep-learning-for-computer-vision-applications-using-matlab.pdfDeep-learning-for-computer-vision-applications-using-matlab.pdf
Deep-learning-for-computer-vision-applications-using-matlab.pdf
 
Convolutional Neural Networks for Image Classification (Cape Town Deep Learni...
Convolutional Neural Networks for Image Classification (Cape Town Deep Learni...Convolutional Neural Networks for Image Classification (Cape Town Deep Learni...
Convolutional Neural Networks for Image Classification (Cape Town Deep Learni...
 
deeplearning
deeplearningdeeplearning
deeplearning
 

Plus de Yan Xu

Kaggle winning solutions: Retail Sales Forecasting
Kaggle winning solutions: Retail Sales ForecastingKaggle winning solutions: Retail Sales Forecasting
Kaggle winning solutions: Retail Sales ForecastingYan Xu
 
Basics of Dynamic programming
Basics of Dynamic programming Basics of Dynamic programming
Basics of Dynamic programming Yan Xu
 
Walking through Tensorflow 2.0
Walking through Tensorflow 2.0Walking through Tensorflow 2.0
Walking through Tensorflow 2.0Yan Xu
 
Practical contextual bandits for business
Practical contextual bandits for businessPractical contextual bandits for business
Practical contextual bandits for businessYan Xu
 
Introduction to Multi-armed Bandits
Introduction to Multi-armed BanditsIntroduction to Multi-armed Bandits
Introduction to Multi-armed BanditsYan Xu
 
A Data-Driven Question Generation Model for Educational Content - by Jack Wang
A Data-Driven Question Generation Model for Educational Content - by Jack WangA Data-Driven Question Generation Model for Educational Content - by Jack Wang
A Data-Driven Question Generation Model for Educational Content - by Jack WangYan Xu
 
Deep Learning Approach in Characterizing Salt Body on Seismic Images - by Zhe...
Deep Learning Approach in Characterizing Salt Body on Seismic Images - by Zhe...Deep Learning Approach in Characterizing Salt Body on Seismic Images - by Zhe...
Deep Learning Approach in Characterizing Salt Body on Seismic Images - by Zhe...Yan Xu
 
Deep Hierarchical Profiling & Pattern Discovery: Application to Whole Brain R...
Deep Hierarchical Profiling & Pattern Discovery: Application to Whole Brain R...Deep Hierarchical Profiling & Pattern Discovery: Application to Whole Brain R...
Deep Hierarchical Profiling & Pattern Discovery: Application to Whole Brain R...Yan Xu
 
Detecting anomalies on rotating equipment using Deep Stacked Autoencoders - b...
Detecting anomalies on rotating equipment using Deep Stacked Autoencoders - b...Detecting anomalies on rotating equipment using Deep Stacked Autoencoders - b...
Detecting anomalies on rotating equipment using Deep Stacked Autoencoders - b...Yan Xu
 
Introduction to Autoencoders
Introduction to AutoencodersIntroduction to Autoencoders
Introduction to AutoencodersYan Xu
 
State of enterprise data science
State of enterprise data scienceState of enterprise data science
State of enterprise data scienceYan Xu
 
Long Short Term Memory
Long Short Term MemoryLong Short Term Memory
Long Short Term MemoryYan Xu
 
Deep Feed Forward Neural Networks and Regularization
Deep Feed Forward Neural Networks and RegularizationDeep Feed Forward Neural Networks and Regularization
Deep Feed Forward Neural Networks and RegularizationYan Xu
 
Linear algebra and probability (Deep Learning chapter 2&3)
Linear algebra and probability (Deep Learning chapter 2&3)Linear algebra and probability (Deep Learning chapter 2&3)
Linear algebra and probability (Deep Learning chapter 2&3)Yan Xu
 
HML: Historical View and Trends of Deep Learning
HML: Historical View and Trends of Deep LearningHML: Historical View and Trends of Deep Learning
HML: Historical View and Trends of Deep LearningYan Xu
 
Secrets behind AlphaGo
Secrets behind AlphaGoSecrets behind AlphaGo
Secrets behind AlphaGoYan Xu
 
Optimization in Deep Learning
Optimization in Deep LearningOptimization in Deep Learning
Optimization in Deep LearningYan Xu
 
Introduction to Neural Network
Introduction to Neural NetworkIntroduction to Neural Network
Introduction to Neural NetworkYan Xu
 
Nonlinear dimension reduction
Nonlinear dimension reductionNonlinear dimension reduction
Nonlinear dimension reductionYan Xu
 
Mean shift and Hierarchical clustering
Mean shift and Hierarchical clustering Mean shift and Hierarchical clustering
Mean shift and Hierarchical clustering Yan Xu
 

Plus de Yan Xu (20)

Kaggle winning solutions: Retail Sales Forecasting
Kaggle winning solutions: Retail Sales ForecastingKaggle winning solutions: Retail Sales Forecasting
Kaggle winning solutions: Retail Sales Forecasting
 
Basics of Dynamic programming
Basics of Dynamic programming Basics of Dynamic programming
Basics of Dynamic programming
 
Walking through Tensorflow 2.0
Walking through Tensorflow 2.0Walking through Tensorflow 2.0
Walking through Tensorflow 2.0
 
Practical contextual bandits for business
Practical contextual bandits for businessPractical contextual bandits for business
Practical contextual bandits for business
 
Introduction to Multi-armed Bandits
Introduction to Multi-armed BanditsIntroduction to Multi-armed Bandits
Introduction to Multi-armed Bandits
 
A Data-Driven Question Generation Model for Educational Content - by Jack Wang
A Data-Driven Question Generation Model for Educational Content - by Jack WangA Data-Driven Question Generation Model for Educational Content - by Jack Wang
A Data-Driven Question Generation Model for Educational Content - by Jack Wang
 
Deep Learning Approach in Characterizing Salt Body on Seismic Images - by Zhe...
Deep Learning Approach in Characterizing Salt Body on Seismic Images - by Zhe...Deep Learning Approach in Characterizing Salt Body on Seismic Images - by Zhe...
Deep Learning Approach in Characterizing Salt Body on Seismic Images - by Zhe...
 
Deep Hierarchical Profiling & Pattern Discovery: Application to Whole Brain R...
Deep Hierarchical Profiling & Pattern Discovery: Application to Whole Brain R...Deep Hierarchical Profiling & Pattern Discovery: Application to Whole Brain R...
Deep Hierarchical Profiling & Pattern Discovery: Application to Whole Brain R...
 
Detecting anomalies on rotating equipment using Deep Stacked Autoencoders - b...
Detecting anomalies on rotating equipment using Deep Stacked Autoencoders - b...Detecting anomalies on rotating equipment using Deep Stacked Autoencoders - b...
Detecting anomalies on rotating equipment using Deep Stacked Autoencoders - b...
 
Introduction to Autoencoders
Introduction to AutoencodersIntroduction to Autoencoders
Introduction to Autoencoders
 
State of enterprise data science
State of enterprise data scienceState of enterprise data science
State of enterprise data science
 
Long Short Term Memory
Long Short Term MemoryLong Short Term Memory
Long Short Term Memory
 
Deep Feed Forward Neural Networks and Regularization
Deep Feed Forward Neural Networks and RegularizationDeep Feed Forward Neural Networks and Regularization
Deep Feed Forward Neural Networks and Regularization
 
Linear algebra and probability (Deep Learning chapter 2&3)
Linear algebra and probability (Deep Learning chapter 2&3)Linear algebra and probability (Deep Learning chapter 2&3)
Linear algebra and probability (Deep Learning chapter 2&3)
 
HML: Historical View and Trends of Deep Learning
HML: Historical View and Trends of Deep LearningHML: Historical View and Trends of Deep Learning
HML: Historical View and Trends of Deep Learning
 
Secrets behind AlphaGo
Secrets behind AlphaGoSecrets behind AlphaGo
Secrets behind AlphaGo
 
Optimization in Deep Learning
Optimization in Deep LearningOptimization in Deep Learning
Optimization in Deep Learning
 
Introduction to Neural Network
Introduction to Neural NetworkIntroduction to Neural Network
Introduction to Neural Network
 
Nonlinear dimension reduction
Nonlinear dimension reductionNonlinear dimension reduction
Nonlinear dimension reduction
 
Mean shift and Hierarchical clustering
Mean shift and Hierarchical clustering Mean shift and Hierarchical clustering
Mean shift and Hierarchical clustering
 

Dernier

GBSN - Microbiology (Unit 1)
GBSN - Microbiology (Unit 1)GBSN - Microbiology (Unit 1)
GBSN - Microbiology (Unit 1)Areesha Ahmad
 
Pests of mustard_Identification_Management_Dr.UPR.pdf
Pests of mustard_Identification_Management_Dr.UPR.pdfPests of mustard_Identification_Management_Dr.UPR.pdf
Pests of mustard_Identification_Management_Dr.UPR.pdfPirithiRaju
 
Hubble Asteroid Hunter III. Physical properties of newly found asteroids
Hubble Asteroid Hunter III. Physical properties of newly found asteroidsHubble Asteroid Hunter III. Physical properties of newly found asteroids
Hubble Asteroid Hunter III. Physical properties of newly found asteroidsSérgio Sacani
 
Botany krishna series 2nd semester Only Mcq type questions
Botany krishna series 2nd semester Only Mcq type questionsBotany krishna series 2nd semester Only Mcq type questions
Botany krishna series 2nd semester Only Mcq type questionsSumit Kumar yadav
 
Spermiogenesis or Spermateleosis or metamorphosis of spermatid
Spermiogenesis or Spermateleosis or metamorphosis of spermatidSpermiogenesis or Spermateleosis or metamorphosis of spermatid
Spermiogenesis or Spermateleosis or metamorphosis of spermatidSarthak Sekhar Mondal
 
Forensic Biology & Its biological significance.pdf
Forensic Biology & Its biological significance.pdfForensic Biology & Its biological significance.pdf
Forensic Biology & Its biological significance.pdfrohankumarsinghrore1
 
Chemistry 4th semester series (krishna).pdf
Chemistry 4th semester series (krishna).pdfChemistry 4th semester series (krishna).pdf
Chemistry 4th semester series (krishna).pdfSumit Kumar yadav
 
Presentation Vikram Lander by Vedansh Gupta.pptx
Presentation Vikram Lander by Vedansh Gupta.pptxPresentation Vikram Lander by Vedansh Gupta.pptx
Presentation Vikram Lander by Vedansh Gupta.pptxgindu3009
 
Labelling Requirements and Label Claims for Dietary Supplements and Recommend...
Labelling Requirements and Label Claims for Dietary Supplements and Recommend...Labelling Requirements and Label Claims for Dietary Supplements and Recommend...
Labelling Requirements and Label Claims for Dietary Supplements and Recommend...Lokesh Kothari
 
Raman spectroscopy.pptx M Pharm, M Sc, Advanced Spectral Analysis
Raman spectroscopy.pptx M Pharm, M Sc, Advanced Spectral AnalysisRaman spectroscopy.pptx M Pharm, M Sc, Advanced Spectral Analysis
Raman spectroscopy.pptx M Pharm, M Sc, Advanced Spectral AnalysisDiwakar Mishra
 
Unlocking the Potential: Deep dive into ocean of Ceramic Magnets.pptx
Unlocking  the Potential: Deep dive into ocean of Ceramic Magnets.pptxUnlocking  the Potential: Deep dive into ocean of Ceramic Magnets.pptx
Unlocking the Potential: Deep dive into ocean of Ceramic Magnets.pptxanandsmhk
 
Nightside clouds and disequilibrium chemistry on the hot Jupiter WASP-43b
Nightside clouds and disequilibrium chemistry on the hot Jupiter WASP-43bNightside clouds and disequilibrium chemistry on the hot Jupiter WASP-43b
Nightside clouds and disequilibrium chemistry on the hot Jupiter WASP-43bSérgio Sacani
 
Hire 💕 9907093804 Hooghly Call Girls Service Call Girls Agency
Hire 💕 9907093804 Hooghly Call Girls Service Call Girls AgencyHire 💕 9907093804 Hooghly Call Girls Service Call Girls Agency
Hire 💕 9907093804 Hooghly Call Girls Service Call Girls AgencySheetal Arora
 
Botany 4th semester file By Sumit Kumar yadav.pdf
Botany 4th semester file By Sumit Kumar yadav.pdfBotany 4th semester file By Sumit Kumar yadav.pdf
Botany 4th semester file By Sumit Kumar yadav.pdfSumit Kumar yadav
 
Lucknow 💋 Russian Call Girls Lucknow Finest Escorts Service 8923113531 Availa...
Lucknow 💋 Russian Call Girls Lucknow Finest Escorts Service 8923113531 Availa...Lucknow 💋 Russian Call Girls Lucknow Finest Escorts Service 8923113531 Availa...
Lucknow 💋 Russian Call Girls Lucknow Finest Escorts Service 8923113531 Availa...anilsa9823
 
Animal Communication- Auditory and Visual.pptx
Animal Communication- Auditory and Visual.pptxAnimal Communication- Auditory and Visual.pptx
Animal Communication- Auditory and Visual.pptxUmerFayaz5
 
Zoology 4th semester series (krishna).pdf
Zoology 4th semester series (krishna).pdfZoology 4th semester series (krishna).pdf
Zoology 4th semester series (krishna).pdfSumit Kumar yadav
 
Pests of cotton_Borer_Pests_Binomics_Dr.UPR.pdf
Pests of cotton_Borer_Pests_Binomics_Dr.UPR.pdfPests of cotton_Borer_Pests_Binomics_Dr.UPR.pdf
Pests of cotton_Borer_Pests_Binomics_Dr.UPR.pdfPirithiRaju
 
Formation of low mass protostars and their circumstellar disks
Formation of low mass protostars and their circumstellar disksFormation of low mass protostars and their circumstellar disks
Formation of low mass protostars and their circumstellar disksSérgio Sacani
 
Physiochemical properties of nanomaterials and its nanotoxicity.pptx
Physiochemical properties of nanomaterials and its nanotoxicity.pptxPhysiochemical properties of nanomaterials and its nanotoxicity.pptx
Physiochemical properties of nanomaterials and its nanotoxicity.pptxAArockiyaNisha
 

Dernier (20)

GBSN - Microbiology (Unit 1)
GBSN - Microbiology (Unit 1)GBSN - Microbiology (Unit 1)
GBSN - Microbiology (Unit 1)
 
Pests of mustard_Identification_Management_Dr.UPR.pdf
Pests of mustard_Identification_Management_Dr.UPR.pdfPests of mustard_Identification_Management_Dr.UPR.pdf
Pests of mustard_Identification_Management_Dr.UPR.pdf
 
Hubble Asteroid Hunter III. Physical properties of newly found asteroids
Hubble Asteroid Hunter III. Physical properties of newly found asteroidsHubble Asteroid Hunter III. Physical properties of newly found asteroids
Hubble Asteroid Hunter III. Physical properties of newly found asteroids
 
Botany krishna series 2nd semester Only Mcq type questions
Botany krishna series 2nd semester Only Mcq type questionsBotany krishna series 2nd semester Only Mcq type questions
Botany krishna series 2nd semester Only Mcq type questions
 
Spermiogenesis or Spermateleosis or metamorphosis of spermatid
Spermiogenesis or Spermateleosis or metamorphosis of spermatidSpermiogenesis or Spermateleosis or metamorphosis of spermatid
Spermiogenesis or Spermateleosis or metamorphosis of spermatid
 
Forensic Biology & Its biological significance.pdf
Forensic Biology & Its biological significance.pdfForensic Biology & Its biological significance.pdf
Forensic Biology & Its biological significance.pdf
 
Chemistry 4th semester series (krishna).pdf
Chemistry 4th semester series (krishna).pdfChemistry 4th semester series (krishna).pdf
Chemistry 4th semester series (krishna).pdf
 
Presentation Vikram Lander by Vedansh Gupta.pptx
Presentation Vikram Lander by Vedansh Gupta.pptxPresentation Vikram Lander by Vedansh Gupta.pptx
Presentation Vikram Lander by Vedansh Gupta.pptx
 
Labelling Requirements and Label Claims for Dietary Supplements and Recommend...
Labelling Requirements and Label Claims for Dietary Supplements and Recommend...Labelling Requirements and Label Claims for Dietary Supplements and Recommend...
Labelling Requirements and Label Claims for Dietary Supplements and Recommend...
 
Raman spectroscopy.pptx M Pharm, M Sc, Advanced Spectral Analysis
Raman spectroscopy.pptx M Pharm, M Sc, Advanced Spectral AnalysisRaman spectroscopy.pptx M Pharm, M Sc, Advanced Spectral Analysis
Raman spectroscopy.pptx M Pharm, M Sc, Advanced Spectral Analysis
 
Unlocking the Potential: Deep dive into ocean of Ceramic Magnets.pptx
Unlocking  the Potential: Deep dive into ocean of Ceramic Magnets.pptxUnlocking  the Potential: Deep dive into ocean of Ceramic Magnets.pptx
Unlocking the Potential: Deep dive into ocean of Ceramic Magnets.pptx
 
Nightside clouds and disequilibrium chemistry on the hot Jupiter WASP-43b
Nightside clouds and disequilibrium chemistry on the hot Jupiter WASP-43bNightside clouds and disequilibrium chemistry on the hot Jupiter WASP-43b
Nightside clouds and disequilibrium chemistry on the hot Jupiter WASP-43b
 
Hire 💕 9907093804 Hooghly Call Girls Service Call Girls Agency
Hire 💕 9907093804 Hooghly Call Girls Service Call Girls AgencyHire 💕 9907093804 Hooghly Call Girls Service Call Girls Agency
Hire 💕 9907093804 Hooghly Call Girls Service Call Girls Agency
 
Botany 4th semester file By Sumit Kumar yadav.pdf
Botany 4th semester file By Sumit Kumar yadav.pdfBotany 4th semester file By Sumit Kumar yadav.pdf
Botany 4th semester file By Sumit Kumar yadav.pdf
 
Lucknow 💋 Russian Call Girls Lucknow Finest Escorts Service 8923113531 Availa...
Lucknow 💋 Russian Call Girls Lucknow Finest Escorts Service 8923113531 Availa...Lucknow 💋 Russian Call Girls Lucknow Finest Escorts Service 8923113531 Availa...
Lucknow 💋 Russian Call Girls Lucknow Finest Escorts Service 8923113531 Availa...
 
Animal Communication- Auditory and Visual.pptx
Animal Communication- Auditory and Visual.pptxAnimal Communication- Auditory and Visual.pptx
Animal Communication- Auditory and Visual.pptx
 
Zoology 4th semester series (krishna).pdf
Zoology 4th semester series (krishna).pdfZoology 4th semester series (krishna).pdf
Zoology 4th semester series (krishna).pdf
 
Pests of cotton_Borer_Pests_Binomics_Dr.UPR.pdf
Pests of cotton_Borer_Pests_Binomics_Dr.UPR.pdfPests of cotton_Borer_Pests_Binomics_Dr.UPR.pdf
Pests of cotton_Borer_Pests_Binomics_Dr.UPR.pdf
 
Formation of low mass protostars and their circumstellar disks
Formation of low mass protostars and their circumstellar disksFormation of low mass protostars and their circumstellar disks
Formation of low mass protostars and their circumstellar disks
 
Physiochemical properties of nanomaterials and its nanotoxicity.pptx
Physiochemical properties of nanomaterials and its nanotoxicity.pptxPhysiochemical properties of nanomaterials and its nanotoxicity.pptx
Physiochemical properties of nanomaterials and its nanotoxicity.pptx
 

Convolutional neural network

  • 1. Deep Learning (2) Convolutional Neural Networks PRESENTED BY HENGYANG (TROY) LU APRIL 22ND, 2017
  • 2. Outlines for Today Section I. Basics of Convolutional Neural Networks ◦ What is CNN? ◦ Comparison with traditional Neural Networks ◦ Why we need CNNs? ◦ Boosting Technologies for CNNs Section II. More Details of Convolutional Neural Networks ◦ AlexNet  A Network for classification  The “Equation” ◦ Optimization Methods in Neural Networks  The Numerical “Solver” Section III. Convolutional Neural Networks with Tensorflow and TFlearn
  • 3. Section I. The Basics Image from http://parse.ele.tue.nl/cluster/2/CNNArchitecture.jpg
  • 4. What is Convolutional Neural Network? What is convolution? ◦ It is a specialized linear operation. ◦ A 2D convolution is shown on the right. (Images From: community.arm.com) ◦ Strictly speaking, it’s cross-correlation. ◦ In CNNs, all convolution operations are actually cross-correlation. Convolutional neural networks are neural networks that use convolution in place of general matrix multiplication in at least one of their layers. They are very powerful in processing data with grid-like topology. [1] [1] Ian Goodfellow, Yoshua Bengio, Aaron Courville , Deep Learning
  • 5. Comparison with MLP In last lecture, we got to know MLP(multi-layer perceptron), where the operation from one layer to neurons in the upper layer is matrix multiplication controlled by weights and bias. In CNNs, where do those “Neurons” go? ◦ Each neuron is one element in the matrix after convolution ◦ weights are shared
  • 6. Comparison with MLP  Local Connections A B C A, with convolution kernel size = 3, the activated neurons are only affected by local neurons , unlike in B, where there are full connections; however, with depth, the receptive field can expand, and get global connections to neurons in lower layer.
  • 7. Why we Need Convolutional Neural Networks? A lot of challenges we could not deal with in the past, now with CNN, yes, we can! :D A lot of things we could do in the past, now with CNN, we can do better! CNNs represent current state-of-the-art technique in classification, object detection etc. Now, let’s take a brief look at these achievements…
  • 8. MNIST Hand-written digits recognition The MNIST database of handwritten digits ◦ Has a training set of 60000 examples, ◦ Has a test set of 10000 examples, ◦ Is a subset of a larger set available from NIST ( National Institute of Standards and Technology) ◦ The digits have been size-normalized (28x28) and centered in a fixed-size image. http://simonwinder.com/2015/07/training-neural-nets-on-mnist-digits/
  • 9. MNIST Classification Record [1] Classifier Preprocessing Best Test Error Rate (%) Linear Classifiers deskewing 7.6 K-Nearest Neighbours Shape-context feature extraction 0.63 Boosted Stumps Haar features 0.87 Non-linear classifiers none 3.3 SVMs deskewing 0.56 Neural Nets none 0.35 Convolution Neural Nets Width normalization 0.23 [1] http://yann.lecun.com/exdb/mnist/
  • 10. The ImageNet Challenge [1][2] The ImageNet Large Scale Visual Recognition Challenge (ILSVRC) is a benchmark in object category classification and detection on hundreds of object categories and millions of images ◦ The ILSVRC challenge has been running annually since 2010, following the footsteps of PASCAL VOC challenge, which was established in 2005. ◦ ILSVRC 2010, 1,461406 images and 1000 object classes. ◦ Images are annotated, and annotations fall into one of two categories ◦ (1) image-level annotation of a binary label for the presence or absence of an object class in the image; ◦ (2) object-level annotation of a tight bounding box and class label around an object instance in the image. ◦ ILSVRC 2017, the last ILSVRC challenge. ◦ In these years, several convolutional neural network structure won the first place: ◦ AlexNet 2012 ◦ InceptionNet 2014 ◦ Deep Residual Network 2015 [1] http://image-net.org/challenges/LSVRC/2017/ [2] Olga Russakovsky et al., ImageNet Large Scale Visual Recognition Challenge
  • 15. Technology Behind PRISMA [1] Deep Convolutional Neural Networks (a) Separate the content and style of an image (b) Recombine the content of one image with the style of another image [1] Leon A. Gatys et al, A Neural Algorithm of Artistic Style
  • 16. Boosting Technology for CNNs The First CNN prototype appeared much earlier, but why it becomes super-hot only in the recent years? ◦ Huge amount of data and advanced storage/memory systems ◦ GPU acceleration which is super fast in convolution operations (Nvidia GPU Tesla K40 1.4 TFlops) ◦ Deep neural network structures ◦ Optimization methods for training the deep CNNs are invented, like stochastic gradient descent ◦ Off-the-shelf software package solutions are available and easy to use ◦ Progress in both hardware and software make CNNs the ONE!
  • 17. Section II: More Details [1] http://www.ritchieng.com/machine-learning/deep-learning/convs/ [1] Slides in section II, credit from slides presented by Tugce Tasci and Kyunghee Kim
  • 20. Architecture Conv L1 Conv L2 Conv L3 Conv L4 Conv L5 Fully Connected L6 Fully Connected L7 Output Layer L8
  • 26. Overlapping Pooling Pooling summarize the outputs of neighbouring groups of neurons in the same kernel map. Two important parameters ◦ Kernel size : z ◦ Stride size: s ◦ If s < z, then the max-pooling is overlapped In the experiment, s=2, z=3 overlapped pooling reduces the top-1 and top-5 error rates by 0.4% and 0.3%, respectively, compared with s=2 and z=2 non-overlapping case.
  • 31. Train the CNNs  Optimization Techniques Back-propagation ◦ Sparse Connections of CNNs decrease the complexity of Back-Propagation ◦ ReLU activation function relieves the vanishing gradient problem Stochastic Gradient Descent
  • 32. Loss Minimization Slide credit from Nadav Cohen, “Adam: A Method for Stochastic Optimization”
  • 33. Large-Scale Setting Slide credit from Nadav Cohen, “Adam: A Method for Stochastic Optimization”
  • 34. Optimization Methods Requirements Slide credit from Nadav Cohen, “Adam: A Method for Stochastic Optimization”
  • 35. Stochastic Gradient Descent (SGD) Slide credit from Nadav Cohen, “Adam: A Method for Stochastic Optimization”
  • 36. Variants to the basic SGD Nestrov’s Accelerated Gradient (SGD) Adaptive Gradient (AdaGrad) Root Mean Square Propagation (RMSProp) Adaptive Moment Estimation (Adam)
  • 37. NAG Slide credit from Nadav Cohen, “Adam: A Method for Stochastic Optimization”
  • 38. AdaGrad Slide credit from Nadav Cohen, “Adam: A Method for Stochastic Optimization”
  • 39. RMSProp Slide credit from Nadav Cohen, “Adam: A Method for Stochastic Optimization”
  • 40. ADAM Slide credit from Nadav Cohen, “Adam: A Method for Stochastic Optimization”
  • 41. ADAM Slide credit from Nadav Cohen, “Adam: A Method for Stochastic Optimization”
  • 42. Comparisons of Different Optimization Methods Slide credit from Nadav Cohen, “Adam: A Method for Stochastic Optimization”
  • 43. Multi-Layer Neural Networks on MNIST Slide credit from Nadav Cohen, “Adam: A Method for Stochastic Optimization”
  • 44. Convolutional Neural Networks on CIFAR-10 Slide credit from Nadav Cohen, “Adam: A Method for Stochastic Optimization”
  • 48. Section III. CNNs with Tensorflow and TFlearn Images from Peter Goldsborough, A Tour of Tensorflow
  • 49. Tensorflow Tensorflow is an open-source library for numerical computation using data flow graphs ◦ Developed by Google Brain Team and Google’s Machine Intelligence research Org. Implementation ML in tensorflow ◦ In tensorflow, computations are represented using Graphs ◦ Each node is an operation (OP) ◦ Data is represented as Tensors ◦ OP takes Tensors and returns Tensors Tensorflow Demo Examples, credit from Jesus Fernandez Bes, “Introduction to convolutional Networks using Tensorflow”
  • 50. Construction of Computational Graph Follow the 3-steps pattern ◦ 1. inference() – Builds the graph as far as is required for running the network forward to make predictions ◦ 2. loss() – Adds to the inference graph the ops required to generate loss ◦ 3. training() – Adds to the loss graph the ops required to compute and apply gradients Tensorflow Demo Examples, credit from Jesus Fernandez Bes, “Introduction to convolutional Networks using Tensorflow”
  • 52. Load the training data, using MNIST from tensorflow.examples.tutorials.mnist import input_data Tensorflow Demo Examples, credit from Jesus Fernandez Bes, “Introduction to convolutional Networks using Tensorflow”
  • 53. Weight Initialization Tensorflow Demo Examples, credit from Jesus Fernandez Bes, “Introduction to convolutional Networks using Tensorflow”
  • 54. Convolution and Pooling Tensorflow Demo Examples, credit from Jesus Fernandez Bes, “Introduction to convolutional Networks using Tensorflow”
  • 55. First Convolutional Layer Tensorflow Demo Examples, credit from Jesus Fernandez Bes, “Introduction to convolutional Networks using Tensorflow”
  • 56. Second Convolutional Layer Tensorflow Demo Examples, credit from Jesus Fernandez Bes, “Introduction to convolutional Networks using Tensorflow”
  • 57. Fully Connected Layer Tensorflow Demo Examples, credit from Jesus Fernandez Bes, “Introduction to convolutional Networks using Tensorflow”
  • 58. Dropout Tensorflow Demo Examples, credit from Jesus Fernandez Bes, “Introduction to convolutional Networks using Tensorflow”
  • 59. Readout Layer Tensorflow Demo Examples, credit from Jesus Fernandez Bes, “Introduction to convolutional Networks using Tensorflow”
  • 60. Train and Evaluate Tensorflow Demo Examples, credit from Jesus Fernandez Bes, “Introduction to convolutional Networks using Tensorflow”
  • 61. Execute Tensorflow Demo Examples, credit from Jesus Fernandez Bes, “Introduction to convolutional Networks using Tensorflow”
  • 62. TFLearn TFLearn is an abstraction library built on top of Tensorflow that provides high-level building blocks to quickly construct TensorFlow graphs. ◦ Highly modular interface ◦ Allow rapid chaining of neural network layers, regularization functions, optimizers and other elements ◦ Can be used with tensorflow hybridly In the following part, let’s implement the previous CNN model with tflearn, and see how much easier life is now! TFLearn Website http://tflearn.org/
  • 63. Redo the same thing with TFLearn Import the packages TFLearn Website http://tflearn.org/
  • 64. Load MNIST dataset TFLearn Website http://tflearn.org/
  • 65. Build the convolutional network TFLearn Website http://tflearn.org/
  • 66. Training the Network TFLearn Website http://tflearn.org/
  • 67. Conclusion Pros: ◦ Deep Convolutional Neural Networks represent current state-of-the-art techniques in image classification, object detection and localization ◦ Powerful CNN models are like AlexNet, InceptionNet, Deep Residual Networks ◦ Open-source libraries for deploying applications with CNNs very fast ◦ Convolutional Neural Networks can share pre-trained weights, which is the basis for transfer learning Cons: ◦ The interpretation and mechanism of CNNs are not clear, we don’t know why they work better than previous models ◦ Large number of training data and annotations are needed, which may not be practical in some problems.