The document discusses the fundamentals of deep learning, particularly through the use of Convolutional Neural Networks (CNNs) for image processing and classification. It outlines key components such as convolutional layers, activation functions, and pooling techniques, and emphasizes the importance of feature extraction and dimensionality reduction. The content also addresses practical applications of CNNs, techniques for dataset creation, and the learning process involving backpropagation.

1. Data Science
Bootcamp
Commencez votre carrière
dans la Data

2. Nos Speakers
—
Cristina Oprean & Pierre Stefani
Machine Learning Engineer

3. The Rise of Deep Learning
Healthcare
Autonomous vehicles
Reinforcement learning
Robotics
Language
Processing
GANs

4. What is Deep Learning ?

5. Why Deep Learning ?
Hand engineered features are time consuming, brittle and
not scalable in practice
Can we learn the underlying features directly from data?

6. Why now ?
Neural Networks date back decades, so why the resurgence?

7. Inspired from neuroscience
- Signal Input
- Neuron activation
Decision

8. Fully connected networks
Fully connected:
Connect neuron in hidden layer to all
neurons in input layer
No spatial information!
And many, many parameters!
Input:
2D image
Vector of pixel values

9. Using spatial structure
Idea: connect patches of input to neurons
in the hidden layer.
Neuron connected to region of input. Only
“sees” these values
Input: 2D image.
Array of pixel values

10. Applying Filters to Extract Features
1) Apply a set of weights – a filter – to extract local features
2) Use multiple filters to extract different features
3) Spatially share parameters of each filter

11. Convolutional Neural Networks

12. Layers used to build ConvNets
INPUT → will hold the raw pixel values of the image (e.g.[32,32,3] - image with width 32,
height 32 and 3 channels: RGB)
Convolutional layer (CONV) → compute the output of neurons connected to
local regions in the input (e.g.: output of size [32x32x12] if we decided to use 12 filters)
RELU → apply an elementwise activation function, such as the max(0,x) thresholding at
zero. (e.g. the size of the volume is unchanged [32x32x12])
POOL → perform a downsampling operation along the spatial dimensions (width, height),
resulting in volume such as [16x16x12].
Fully connected layer (FC) → compute the class scores, and it connects all
neurons in this layer with all the neurons in the previous one. (e.g. the size is [1, 1, 10] if we
have 10 classes)

13. Input layer
Existing color spaces for images:
RBG, Grayscale, HSV, Lab, etc.
CNNs - architectures specific for
images
Reduce the images into a form
easier to process
Without loosing features needed
for a good recognition

14. Convolutional layer (CONV)
Spatial arrangement:
Depths (D) → nb of filters we want to
use
Stride (S) → value with which we slide
the filter
Padding (P) → the number of zeros we
add to the border
Input size (I) → size of the image
Filter size (F) → size of the convolution
=> Size of the output:
(I−F+2P)/S+1
E.g. i=5, F=3, P=0, S=1 => O=(5-3+0)/1+1=3

15. Convolutional layer (CONV)
Conv layers:
In CNNs architectures can
have multiple Conv layers
1st layer captures low-level
features
Final layers capture
high-level features
When the image has 3 channels (RGB) => the filter has D = 3

16. Pooling layer (POOL)
Reduces the spatial size of the
convolved feature
Decreases computational power
Extracts dominant features
Has no parameters to learn
Two types: max and average pooling

17. Pooling layer (POOL)
Max pooling performs better than
average pooling
Max pooling is a noise
suppressant

18. RELU (activation function)
Introduces
non-linearities into
the network

19. RELU (activation function)
Linear Activation functions
produce linear decisions no
matter the network size
Non-linearities allow us to
approximate arbitrarily
complex functions

20. CNNs for feature learning
1. Learn features in input image through convolution
2. Introduce non-linearity through activation function (real-world data is non-linear!)
3. Reduce dimensionality and preserve spatial invariance with pooling

21. CNNs for classification
1. CONV and POOL layers output high-level features of input
2. Fully connected layer uses these features for classifying input image
3. Express output as probability of image belonging to a particular class

22. CNNs: training with backpropagation
Learn weights for convolutional filters and fully connected layers

23. ConvNet architectures
LeNet
AlexNet
GoogLeNet
VGGNet
ResNet
etc.
Errorrate%

24. CNNs: Tips - dataset creation
Where to find datasets
https://toolbox.google.com/datasetsearch
https://www.kaggle.com/datasets
Crawl the web ! (Flickr, Bing, Google)
Watch out for scientific paper releases and conference workshops

26. CNNs: Tips - training
● No need to start from scratch (train with less data, start from pretrained models,
domain adaptation)
● Monitor loss and validation accuracies
● Optimize once it works
Batch size
Learning Rates
Modules & Loss

27. Some applications @Photobox
and not only

28. Photo crop: naive version
⇒ How to crop the photo and keep the main subject ?

29. Photo crop: using face detection
⇒ Face detection allows to have a crop focused on the faces

30. Near duplicates filtering
Without duplicates
filtering
With duplicates
filtering

31. Near duplicates filtering
0.4
0
0.1
…
0
Remove
Feature comparison allows us to find near duplicates and remove them
Goal : reduce the hassle of duplicate selection

32. Near duplicates filtering
Goal : reduce the hassle of duplicate selection
Feature comparison allows us to find near duplicates and remove them
0.4
5
-3
…
3
Remove

33. Near duplicates filtering
-4
15
20
…
10
Remove
Feature comparison allows us to find near duplicates and remove them
Goal : reduce the hassle of duplicate selection

34. Feature comparison allows us to find near duplicates and remove them
-40
5
10
…
11
Remove
Near duplicates filtering
Goal : reduce the hassle of duplicate selection

35. Feature comparison allows us to find near duplicates and remove them
102
-32
120
…
33
Keep
Near duplicates filtering
Goal : reduce the hassle of duplicate selection

36. Photo selection with aesthetics
● Propose book covers or photo candidates for full page photos in a book
● Suggest premium products with the most beautiful pictures from a set

37. Photo selection with aesthetics
● Select the most beautiful photo from a set of duplicates
0.73
0.52
0.53
0.67

38. Style transfer
38

39. Let’s pratice !

40. How it ‘learns’: minimizing the error
input
expected
output expected
output
output
‘ cat ‘
Error
(ou loss)

41. How it ‘learns’ : minimizing the error
minimum
Starting
point

42. How it ‘learns’: minimizing the error
minimum
Starting
point

43. How it ‘learns’: backpropagation
input
expected
output
output
Error
(ou loss)

44. Takeaways
No algorithm is 100% accurate
It depends on:
How much data we have
The quality of the data
Performance tradeoff
Hardware
Some algorithms are better than humans,
some of them are way behind

47. How it ‘learns’ : minimizing the error
- Define a loss function
- Minimize this loss
- Gradient descent
algorithm