SlideShare una empresa de Scribd logo
1 de 70
Facebook!
Clarifai
Let’s reveal the mystery!
Neural Nets
What this can do!
Let’s start with a node
Architecture
Forward Pass
•Calculating the loss
Backward Pass
•Backpropagation Algorithm
•Distributing Gradients
Optimizing
•Reducing the loss
•Updating the weight matrix
Updating weights
Loss FunctionUpdating weights
YOU CAN’T TRAIN
IF THERE ARE NO GRADIENTS
This went deeper!
How ?
With the help of two superheros!
Deep Neural Networks
What makes this special?
Hierarchical Feature Representation
Why this feature thing is so effective ?
Then what happened ?
Deep Neural Nets became harder and harder to train!
DEEP NETS!
Y U NO EASY?
Number Of Parameters?
These nets are huge!
Millions of layers
Millions of nodes
Billions of parameters
BUT DON’T KNOW HOW
MANY HIDDEN LAYERS /
NODES TO USE?
WHEN YOU WANT TO
BUILD A NEURAL NET
Overfitting
Killing the training process
Neuron in a neural network
Sigmoid activation function
Too much connections ?
What if we input some exact features!
Feature Engineering
Canny edge detection filter
How we see things ?
Important!
Not all pixels!
But patterns of pixels!
This is fast!
Right to left ?
Can you remember
NOT EVERYTHING
BUT IMPORTANT THINGS!
Can we design set of features for
machines ??
No way!
We may design some high level features!
But our machines deal with PIXELS!
What if we let the machine to
extract it’s own features!
Wow that was nice :)
BRACE YOURSELVES
CNN IS COMING
Imagenet Challenge
Step by step
ConvNets have one layer called CN layer after the input layer
This act as an automatic feature extractor
Additional Layers!
Convolution layer
RELU layer (Nonlinearity)
Max pooling layer
Amazing local connectivity
Let’s go layerwise!
Convolutional Layer
This is simply applying convolution to input pixels
Now! What is convolution?
Mathematical way
Easy way!
For an image
CONVOLUTION
EVERYWHERE
More generally...
Filter search for things in the image
When filter sees something similar to
it’s orientation in an image it will fire
up!
Image get transformed into
something new !
We call this new image as a feature map
Because it mapps some features from the original
image w.r.t to the filter!
Right - Feature map obtained by applying canny edge filter on an image
It’s not only a single filter!
Many filters searching for diffrent things!
How amazing!
So we will have different feature maps!
Simply each filter has it’s own task
Gabor filters are similar to those of the human visual system, and
they have been found to be particularly appropriate for texture
representation and discrimination.
How filter weights
looking at an image!
This is how it’s done!
Feature maps = Set of neurones
That’s convolution layer!
But where’s the magic ?
All these filters are trainable!
Means ?
These are not man made filters!
Look at the values of following filter kernels
What about the filter?
We can design size , channels of the filter
But not its values!
Each filter values is trainable weight
All in one!
So every filter values is trainable
It’s like a set of weights !
But how ?
With backprop
Convolution is a perfectly differentiable function!
So we can learn it’s weight parameters
Reminder!
Then we apply some nonlinearity
We apply rely on each point in the feature maps
Remember : These points in the feature maps are like neurons
This is like just forgetting the negative parts of the
So the orientation be like
Then the pooling layer
This is like a filter without
parameters!
This is for subsample or to
reduce the dimensions of
the feature maps
Simply this will extract the
most important features
from the feature map
That’s basics!
Lenet
So finally….
We can train these filter weights using backprop and some
kind of optimization algorithms(Adam)
Here’s a such view of a trained filter
Motivation!
Q & A !

Más contenido relacionado

Destacado

Backpropagation in Convolutional Neural Network
Backpropagation in Convolutional Neural NetworkBackpropagation in Convolutional Neural Network
Backpropagation in Convolutional Neural Network
Hiroshi Kuwajima
 

Destacado (16)

Time Series Analysis/ Forecasting
Time Series Analysis/ Forecasting  Time Series Analysis/ Forecasting
Time Series Analysis/ Forecasting
 
quick intro to elastic search
quick intro to elastic search quick intro to elastic search
quick intro to elastic search
 
What I learnt: Elastic search & Kibana : introduction, installtion & configur...
What I learnt: Elastic search & Kibana : introduction, installtion & configur...What I learnt: Elastic search & Kibana : introduction, installtion & configur...
What I learnt: Elastic search & Kibana : introduction, installtion & configur...
 
Deep Learning - Convolutional Neural Networks - Architectural Zoo
Deep Learning - Convolutional Neural Networks - Architectural ZooDeep Learning - Convolutional Neural Networks - Architectural Zoo
Deep Learning - Convolutional Neural Networks - Architectural Zoo
 
Backpropagation in Convolutional Neural Network
Backpropagation in Convolutional Neural NetworkBackpropagation in Convolutional Neural Network
Backpropagation in Convolutional Neural Network
 
An Introduction to Elastic Search.
An Introduction to Elastic Search.An Introduction to Elastic Search.
An Introduction to Elastic Search.
 
Deep Learning - Convolutional Neural Networks
Deep Learning - Convolutional Neural NetworksDeep Learning - Convolutional Neural Networks
Deep Learning - Convolutional Neural Networks
 
Hype vs. Reality: The AI Explainer
Hype vs. Reality: The AI ExplainerHype vs. Reality: The AI Explainer
Hype vs. Reality: The AI Explainer
 
What Makes Great Infographics
What Makes Great InfographicsWhat Makes Great Infographics
What Makes Great Infographics
 
Masters of SlideShare
Masters of SlideShareMasters of SlideShare
Masters of SlideShare
 
STOP! VIEW THIS! 10-Step Checklist When Uploading to Slideshare
STOP! VIEW THIS! 10-Step Checklist When Uploading to SlideshareSTOP! VIEW THIS! 10-Step Checklist When Uploading to Slideshare
STOP! VIEW THIS! 10-Step Checklist When Uploading to Slideshare
 
You Suck At PowerPoint!
You Suck At PowerPoint!You Suck At PowerPoint!
You Suck At PowerPoint!
 
10 Ways to Win at SlideShare SEO & Presentation Optimization
10 Ways to Win at SlideShare SEO & Presentation Optimization10 Ways to Win at SlideShare SEO & Presentation Optimization
10 Ways to Win at SlideShare SEO & Presentation Optimization
 
How To Get More From SlideShare - Super-Simple Tips For Content Marketing
How To Get More From SlideShare - Super-Simple Tips For Content MarketingHow To Get More From SlideShare - Super-Simple Tips For Content Marketing
How To Get More From SlideShare - Super-Simple Tips For Content Marketing
 
3 Things Every Sales Team Needs to Be Thinking About in 2017
3 Things Every Sales Team Needs to Be Thinking About in 20173 Things Every Sales Team Needs to Be Thinking About in 2017
3 Things Every Sales Team Needs to Be Thinking About in 2017
 
Getting Started With SlideShare
Getting Started With SlideShareGetting Started With SlideShare
Getting Started With SlideShare
 

Similar a Introduction to Convolutional Neural Nets

What is jubatus? How it works for you?
What is jubatus? How it works for you?What is jubatus? How it works for you?
What is jubatus? How it works for you?
Kumazaki Hiroki
 

Similar a Introduction to Convolutional Neural Nets (20)

Neural Networks and Deep Learning Basics
Neural Networks and Deep Learning BasicsNeural Networks and Deep Learning Basics
Neural Networks and Deep Learning Basics
 
Python for Image Understanding: Deep Learning with Convolutional Neural Nets
Python for Image Understanding: Deep Learning with Convolutional Neural NetsPython for Image Understanding: Deep Learning with Convolutional Neural Nets
Python for Image Understanding: Deep Learning with Convolutional Neural Nets
 
Lets build a neural network
Lets build a neural networkLets build a neural network
Lets build a neural network
 
Deep learning introduction
Deep learning introductionDeep learning introduction
Deep learning introduction
 
ANN.ppt[1].pptx
ANN.ppt[1].pptxANN.ppt[1].pptx
ANN.ppt[1].pptx
 
cnn ppt.pptx
cnn ppt.pptxcnn ppt.pptx
cnn ppt.pptx
 
Deep Learning Sample Class (Jon Lederman)
Deep Learning Sample Class (Jon Lederman)Deep Learning Sample Class (Jon Lederman)
Deep Learning Sample Class (Jon Lederman)
 
Version ofslideshare
Version ofslideshareVersion ofslideshare
Version ofslideshare
 
ML Module 3 Non Linear Learning.pptx
ML Module 3 Non Linear Learning.pptxML Module 3 Non Linear Learning.pptx
ML Module 3 Non Linear Learning.pptx
 
introduction to DL network deep learning.ppt
introduction to DL network deep learning.pptintroduction to DL network deep learning.ppt
introduction to DL network deep learning.ppt
 
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
 
Convolutional neural network complete guide
Convolutional neural network complete guideConvolutional neural network complete guide
Convolutional neural network complete guide
 
Don't Start from Scratch: Transfer Learning for Novel Computer Vision Problem...
Don't Start from Scratch: Transfer Learning for Novel Computer Vision Problem...Don't Start from Scratch: Transfer Learning for Novel Computer Vision Problem...
Don't Start from Scratch: Transfer Learning for Novel Computer Vision Problem...
 
Deep Computer Vision - 1.pptx
Deep Computer Vision - 1.pptxDeep Computer Vision - 1.pptx
Deep Computer Vision - 1.pptx
 
What is jubatus? How it works for you?
What is jubatus? How it works for you?What is jubatus? How it works for you?
What is jubatus? How it works for you?
 
Automatic Attendace using convolutional neural network Face Recognition
Automatic Attendace using convolutional neural network Face RecognitionAutomatic Attendace using convolutional neural network Face Recognition
Automatic Attendace using convolutional neural network Face Recognition
 
Introduction to deep learning workshop
Introduction to deep learning workshopIntroduction to deep learning workshop
Introduction to deep learning workshop
 
Neural Networks, Spark MLlib, Deep Learning
Neural Networks, Spark MLlib, Deep LearningNeural Networks, Spark MLlib, Deep Learning
Neural Networks, Spark MLlib, Deep Learning
 
Understanding Deep Learning & Parameter Tuning with MXnet, H2o Package in R
Understanding Deep Learning & Parameter Tuning with MXnet, H2o Package in RUnderstanding Deep Learning & Parameter Tuning with MXnet, H2o Package in R
Understanding Deep Learning & Parameter Tuning with MXnet, H2o Package in R
 
Designing a neural network architecture for image recognition
Designing a neural network architecture for image recognitionDesigning a neural network architecture for image recognition
Designing a neural network architecture for image recognition
 

Último

Top profile Call Girls In Tumkur [ 7014168258 ] Call Me For Genuine Models We...
Top profile Call Girls In Tumkur [ 7014168258 ] Call Me For Genuine Models We...Top profile Call Girls In Tumkur [ 7014168258 ] Call Me For Genuine Models We...
Top profile Call Girls In Tumkur [ 7014168258 ] Call Me For Genuine Models We...
nirzagarg
 
Top profile Call Girls In Hapur [ 7014168258 ] Call Me For Genuine Models We ...
Top profile Call Girls In Hapur [ 7014168258 ] Call Me For Genuine Models We ...Top profile Call Girls In Hapur [ 7014168258 ] Call Me For Genuine Models We ...
Top profile Call Girls In Hapur [ 7014168258 ] Call Me For Genuine Models We ...
nirzagarg
 
Top profile Call Girls In Satna [ 7014168258 ] Call Me For Genuine Models We ...
Top profile Call Girls In Satna [ 7014168258 ] Call Me For Genuine Models We ...Top profile Call Girls In Satna [ 7014168258 ] Call Me For Genuine Models We ...
Top profile Call Girls In Satna [ 7014168258 ] Call Me For Genuine Models We ...
nirzagarg
 
Sealdah % High Class Call Girls Kolkata - 450+ Call Girl Cash Payment 8005736...
Sealdah % High Class Call Girls Kolkata - 450+ Call Girl Cash Payment 8005736...Sealdah % High Class Call Girls Kolkata - 450+ Call Girl Cash Payment 8005736...
Sealdah % High Class Call Girls Kolkata - 450+ Call Girl Cash Payment 8005736...
HyderabadDolls
 
Top profile Call Girls In dimapur [ 7014168258 ] Call Me For Genuine Models W...
Top profile Call Girls In dimapur [ 7014168258 ] Call Me For Genuine Models W...Top profile Call Girls In dimapur [ 7014168258 ] Call Me For Genuine Models W...
Top profile Call Girls In dimapur [ 7014168258 ] Call Me For Genuine Models W...
gajnagarg
 
Computer science Sql cheat sheet.pdf.pdf
Computer science Sql cheat sheet.pdf.pdfComputer science Sql cheat sheet.pdf.pdf
Computer science Sql cheat sheet.pdf.pdf
SayantanBiswas37
 
Jual obat aborsi Bandung ( 085657271886 ) Cytote pil telat bulan penggugur ka...
Jual obat aborsi Bandung ( 085657271886 ) Cytote pil telat bulan penggugur ka...Jual obat aborsi Bandung ( 085657271886 ) Cytote pil telat bulan penggugur ka...
Jual obat aborsi Bandung ( 085657271886 ) Cytote pil telat bulan penggugur ka...
Klinik kandungan
 
Top profile Call Girls In Purnia [ 7014168258 ] Call Me For Genuine Models We...
Top profile Call Girls In Purnia [ 7014168258 ] Call Me For Genuine Models We...Top profile Call Girls In Purnia [ 7014168258 ] Call Me For Genuine Models We...
Top profile Call Girls In Purnia [ 7014168258 ] Call Me For Genuine Models We...
nirzagarg
 
如何办理英国诺森比亚大学毕业证(NU毕业证书)成绩单原件一模一样
如何办理英国诺森比亚大学毕业证(NU毕业证书)成绩单原件一模一样如何办理英国诺森比亚大学毕业证(NU毕业证书)成绩单原件一模一样
如何办理英国诺森比亚大学毕业证(NU毕业证书)成绩单原件一模一样
wsppdmt
 
Jodhpur Park | Call Girls in Kolkata Phone No 8005736733 Elite Escort Service...
Jodhpur Park | Call Girls in Kolkata Phone No 8005736733 Elite Escort Service...Jodhpur Park | Call Girls in Kolkata Phone No 8005736733 Elite Escort Service...
Jodhpur Park | Call Girls in Kolkata Phone No 8005736733 Elite Escort Service...
HyderabadDolls
 
In Riyadh ((+919101817206)) Cytotec kit @ Abortion Pills Saudi Arabia
In Riyadh ((+919101817206)) Cytotec kit @ Abortion Pills Saudi ArabiaIn Riyadh ((+919101817206)) Cytotec kit @ Abortion Pills Saudi Arabia
In Riyadh ((+919101817206)) Cytotec kit @ Abortion Pills Saudi Arabia
ahmedjiabur940
 

Último (20)

Top profile Call Girls In Tumkur [ 7014168258 ] Call Me For Genuine Models We...
Top profile Call Girls In Tumkur [ 7014168258 ] Call Me For Genuine Models We...Top profile Call Girls In Tumkur [ 7014168258 ] Call Me For Genuine Models We...
Top profile Call Girls In Tumkur [ 7014168258 ] Call Me For Genuine Models We...
 
Top profile Call Girls In Hapur [ 7014168258 ] Call Me For Genuine Models We ...
Top profile Call Girls In Hapur [ 7014168258 ] Call Me For Genuine Models We ...Top profile Call Girls In Hapur [ 7014168258 ] Call Me For Genuine Models We ...
Top profile Call Girls In Hapur [ 7014168258 ] Call Me For Genuine Models We ...
 
Top profile Call Girls In Satna [ 7014168258 ] Call Me For Genuine Models We ...
Top profile Call Girls In Satna [ 7014168258 ] Call Me For Genuine Models We ...Top profile Call Girls In Satna [ 7014168258 ] Call Me For Genuine Models We ...
Top profile Call Girls In Satna [ 7014168258 ] Call Me For Genuine Models We ...
 
Kings of Saudi Arabia, information about them
Kings of Saudi Arabia, information about themKings of Saudi Arabia, information about them
Kings of Saudi Arabia, information about them
 
Gulbai Tekra * Cheap Call Girls In Ahmedabad Phone No 8005736733 Elite Escort...
Gulbai Tekra * Cheap Call Girls In Ahmedabad Phone No 8005736733 Elite Escort...Gulbai Tekra * Cheap Call Girls In Ahmedabad Phone No 8005736733 Elite Escort...
Gulbai Tekra * Cheap Call Girls In Ahmedabad Phone No 8005736733 Elite Escort...
 
Sealdah % High Class Call Girls Kolkata - 450+ Call Girl Cash Payment 8005736...
Sealdah % High Class Call Girls Kolkata - 450+ Call Girl Cash Payment 8005736...Sealdah % High Class Call Girls Kolkata - 450+ Call Girl Cash Payment 8005736...
Sealdah % High Class Call Girls Kolkata - 450+ Call Girl Cash Payment 8005736...
 
5CL-ADBA,5cladba, Chinese supplier, safety is guaranteed
5CL-ADBA,5cladba, Chinese supplier, safety is guaranteed5CL-ADBA,5cladba, Chinese supplier, safety is guaranteed
5CL-ADBA,5cladba, Chinese supplier, safety is guaranteed
 
Top profile Call Girls In dimapur [ 7014168258 ] Call Me For Genuine Models W...
Top profile Call Girls In dimapur [ 7014168258 ] Call Me For Genuine Models W...Top profile Call Girls In dimapur [ 7014168258 ] Call Me For Genuine Models W...
Top profile Call Girls In dimapur [ 7014168258 ] Call Me For Genuine Models W...
 
Computer science Sql cheat sheet.pdf.pdf
Computer science Sql cheat sheet.pdf.pdfComputer science Sql cheat sheet.pdf.pdf
Computer science Sql cheat sheet.pdf.pdf
 
Dubai Call Girls Peeing O525547819 Call Girls Dubai
Dubai Call Girls Peeing O525547819 Call Girls DubaiDubai Call Girls Peeing O525547819 Call Girls Dubai
Dubai Call Girls Peeing O525547819 Call Girls Dubai
 
Jual obat aborsi Bandung ( 085657271886 ) Cytote pil telat bulan penggugur ka...
Jual obat aborsi Bandung ( 085657271886 ) Cytote pil telat bulan penggugur ka...Jual obat aborsi Bandung ( 085657271886 ) Cytote pil telat bulan penggugur ka...
Jual obat aborsi Bandung ( 085657271886 ) Cytote pil telat bulan penggugur ka...
 
Top Call Girls in Balaghat 9332606886Call Girls Advance Cash On Delivery Ser...
Top Call Girls in Balaghat  9332606886Call Girls Advance Cash On Delivery Ser...Top Call Girls in Balaghat  9332606886Call Girls Advance Cash On Delivery Ser...
Top Call Girls in Balaghat 9332606886Call Girls Advance Cash On Delivery Ser...
 
Top profile Call Girls In Purnia [ 7014168258 ] Call Me For Genuine Models We...
Top profile Call Girls In Purnia [ 7014168258 ] Call Me For Genuine Models We...Top profile Call Girls In Purnia [ 7014168258 ] Call Me For Genuine Models We...
Top profile Call Girls In Purnia [ 7014168258 ] Call Me For Genuine Models We...
 
如何办理英国诺森比亚大学毕业证(NU毕业证书)成绩单原件一模一样
如何办理英国诺森比亚大学毕业证(NU毕业证书)成绩单原件一模一样如何办理英国诺森比亚大学毕业证(NU毕业证书)成绩单原件一模一样
如何办理英国诺森比亚大学毕业证(NU毕业证书)成绩单原件一模一样
 
Jodhpur Park | Call Girls in Kolkata Phone No 8005736733 Elite Escort Service...
Jodhpur Park | Call Girls in Kolkata Phone No 8005736733 Elite Escort Service...Jodhpur Park | Call Girls in Kolkata Phone No 8005736733 Elite Escort Service...
Jodhpur Park | Call Girls in Kolkata Phone No 8005736733 Elite Escort Service...
 
Digital Transformation Playbook by Graham Ware
Digital Transformation Playbook by Graham WareDigital Transformation Playbook by Graham Ware
Digital Transformation Playbook by Graham Ware
 
Ranking and Scoring Exercises for Research
Ranking and Scoring Exercises for ResearchRanking and Scoring Exercises for Research
Ranking and Scoring Exercises for Research
 
Aspirational Block Program Block Syaldey District - Almora
Aspirational Block Program Block Syaldey District - AlmoraAspirational Block Program Block Syaldey District - Almora
Aspirational Block Program Block Syaldey District - Almora
 
In Riyadh ((+919101817206)) Cytotec kit @ Abortion Pills Saudi Arabia
In Riyadh ((+919101817206)) Cytotec kit @ Abortion Pills Saudi ArabiaIn Riyadh ((+919101817206)) Cytotec kit @ Abortion Pills Saudi Arabia
In Riyadh ((+919101817206)) Cytotec kit @ Abortion Pills Saudi Arabia
 
Fun all Day Call Girls in Jaipur 9332606886 High Profile Call Girls You Ca...
Fun all Day Call Girls in Jaipur   9332606886  High Profile Call Girls You Ca...Fun all Day Call Girls in Jaipur   9332606886  High Profile Call Girls You Ca...
Fun all Day Call Girls in Jaipur 9332606886 High Profile Call Girls You Ca...
 

Introduction to Convolutional Neural Nets

Notas del editor

  1. This is why we need to go bit deeper. We need to
  2. Simple architecture Set of weights , line Output classes Training data
  3. How a trained system take decisions
  4. Simple introduction to smallest unit of a neural network How dot product and non linearity is applied
  5. Forward pass Loss function Reducing the loss Tweaking the weights
  6. Generally speaking the importance of gradients and backward pass
  7. Very brief idea
  8. What is happening in the training
  9. Somehow u should calculate the gradietns
  10. At that time these networks outperformed all the things .. so they needed to develop this deeper ..
  11. Give them number of nodes parameters and weights increased with line Same process
  12. The hierarchical feature representation and classifying
  13. Botom to top approach
  14. Will explain how brain would like to see things in brief . They use a cortex of a cat
  15. Why people had to move from deep neural nets
  16. Give them the idea of how many nodes and how many parameters has increased
  17. Give them the idea they nets are complex and have many things to calculate
  18. Very brief
  19. Mathematical complexity
  20. Main problem
  21. What are the feature extraction methods , how people do those things
  22. Feature engineering
  23. This is like deciding of making a filter
  24. We can clearly use some features like their coat! So this is more of using right features at right time that’s why we are so fast
  25. We don’t work with the pixels. We use some high level features
  26. New wway of thingking
  27. Brief introduction on imagent . How alexnet won the competition and boosted the concept of CNN
  28. Convolution layers , their positions , feature mapts then again same thing How feature map has one neuron thing
  29. Explaining we we add additional layers
  30. Very important .. local conectivity .. why it’s important .. why we can learn inside patter Not like the all connected things
  31. Brief architecture how this thing can be done
  32. Layered architecture
  33. Briefly talk about what happening. And dot product .. size of the kernal , what is generated by using kernal
  34. Not going to talk about this :D
  35. This is 2D convolution. But in CNN it’s all about 3D convolution
  36. This is to understand what is happening
  37. General meaning of applying a filter.
  38. General meanign of a feature map
  39. Now what happened when many filter search for many things. This can create a layer of feature maps Many filters trying to dig many things
  40. How different filters aligned How filters go in spatial direction and find the orientations of pixels. Each filters trying to find new things
  41. Neuron thing .. Each neuron look at some set of local pixels not all
  42. How different feature maps created
  43. How neuron get generated
  44. Want to explain how these filter params can be trained.
  45. How people found the values .. people diddnet find the values for filteers
  46. Mane made filter ...
  47. But here it’s not like that Do my ow thng
  48. I will explain bit about the hyper params of the filter
  49. Speciality in CNN. and how it learns the kernel values.
  50. Not going in detail. But will say why these differentiable functions are useful for deep nets cz of the back prop
  51. Will only speak up to the feature map Will talk about the depth of the feature maps layer Will talk about the spatial values of each filter
  52. Rrelu. Won’t talk much
  53. Real world netowork
  54. Pooling won’t talk much. But will explain how reducing of params can be done
  55. Explaining about the net Recursive behavior of it!