The document is a presentation about TensorFlow. It begins with an introduction that defines machine learning and deep learning. It then discusses what TensorFlow is, including that it is an open-source library for deep learning and ML, was developed by Google Brain, and uses data flow graphs to represent computations. The presentation explains benefits of TensorFlow like parallelism, distributed execution, and portability. It provides examples of companies using TensorFlow and demonstrates cool projects that can be built with it, like image classification, object detection, and speech recognition. Finally, it concludes that TensorFlow is helping achieve amazing advancements in machine learning.

1. #Fantastic4
Organized By
ESEN Android Club

2. Hello!
I am Rebai Ahmed
I am here because I love to give presentations && I love Tensorflow
Check out my portfolio rebai.ahmed.github.io
2

3. Plan
3
➢ Introduction
➢ What is Tensorflow ?
➢ Why Tensorflow ?
➢ Cool Projects with Tensorflow
➢ Conclusion

4. Quick Questions
➢ How many people have heard about Deep Learning | Machine learning |
tensorflow ?
➢ How many people know about Deep Learning | Machine learning | tensorflow
?
➢ How many people are using Deep Learning | Machine learning | tensorflow ?
4

5. 1. Introduction
Artificial Intelligence, deep learning, machine learning —
whatever you’re doing if you don’t understand it — learn it.
Because otherwise you’re going to be a dinosaur within 3 years.
Mark Cuban

6. Introduction : What is Machine learning ?

7. ★ Subfield of Artificial Intelligence (AI) gives "computers the ability to
learn without being explicitly programmed"
★ Machine learning is preferred approach to :
➢ Weather prediction
➢ Recommendation systems
➢ Spam Filtering
7
Introduction : What is Machine learning (2) ?

8. 8
Introduction : What is Deep Learning ?
Deep Learning is a subfield of Machine
learning concerned with algorithms inspired by
the structure and the function of the brain called
artificial neural network.

9. 9
Introduction : What is Deep Learning ?
➢ Our brain has lots of neurons connected
together and the strength of
the connections between neurons
represents long term knowledge.
Neurons in the brain

10. 10
Introduction : What is Deep Learning ?
Neural Network (Deep Learning)

11. 11
Introduction : Deep learning Why Now ?

12. 12
Introduction : Deep learning Why Now ?
➢ Big DATA
➢ big processing power
➢ robust neural networks

13. 13
Tools

14. 2. What is TensorFlow ?
● TensorFlow is an open-source library for Deep Learning and Machine learning
● Developed by the Google Brain team and released in November 2015
● TensorFlow is mainly used for: Classification, Perception, Understanding,
Discovering, Prediction and Creation
14

15. 2. What is TensorFlow ?
TensorFlow = Tensor + Flow = Data +
Flow
15

16. 2. But What is Tensor ?
An n-dimensional array :
➢ 0-d tensor: scalar (number)
➢ 1-d tensor: vector
➢ 2-d tensor: matrix
➢ and so on
16

17. 2. But What is Tensor Flow?
Data Flow Graphs
➢ Dataflow is a common programming model for
parallel computing.
➢ TensorFlow uses a dataflow graph to
represent your computation
17

18. 2. What are the benefits of using graphs ?
➢ Parallelism. ( it is easy for the system to identify operations that can
execute in parallel )
➢ Distributed execution ( it is possible for TensorFlow to partition your program
across multiple devices CPUs, GPUs, and TPUs)
➢ Compilation (generate faster code)
➢ Portability (You can build a dataflow graph in Python, store it in a Saved
Model, and restore it in a C++ program )
18

19. More in Tensorflow:
Machine learning in Javascript
19

20. More in Tensorflow:
➢ It possible to add machine learning capabilities to any web application
➢ You can use the APIs to build and train models right in the browser or in
your Node.js server application
➢ You can use TensorFlow.js to run existing models in your JavaScript
environment.
20

21. 21
Demo1 Tensorflow
Code Demo

22. 3. Why Tensorflow ?
22

23. 23
Why TensorFlow : Runs Everywhere
Runs on desktop and mobile devices such as
● Linux
● macOS
● iOS
● Android
● Raspberry pi
● And Windows

24. 24
Why TensorFlow : Flexibility
● Python API offers flexibility to create all sorts of
computations(Including any neural network
architecture we can think of)
● Includes highly efficient C++ implementations of
many ML operations

25. 25
Why TensorFlow: Parallel Computation
TensorFlow supports distributed computing

26. 26
Why TensorFlow : Large community
● One the the most popular open source projects
on GitHub
● It has a dedicated team of passionate and
helpful developers
● Growing community contributing to improve it

27. 27
Why TensorFlow :Google products
● It powers many of Google’s large-scale services, such as
○ Google Cloud Speech
○ Google Photos and
○ Google Search

28. 28
Why TensorFlow : Big Companies using
Tensorflow
● Google
● OpenAI
● DeepMind
● Uber
● eBay
● DropBox
● A bunch of startups

29. Cool Projects with Tensorflow
Project1 : Image Classification
29

30. Cool Projects with Tensorflow
Project 2: Object Detection
30

31. Cool Projects with Tensorflow
Project 3: Speech recognition
31

32. Cool Projects with Tensorflow
Project 4: Deep learning driven jazz generation
32

33. Cool Projects with Tensorflow
Project 5: Restore colors in B&W photos and videos
33

34. Cool Projects with Tensorflow
Project 6: Transferring style from famous paintings
34

35. 5. Conclusion
There are numerous and amazing things that people
have done using machine learning, some of which include
applications relating to health care, recommendation engines
for movies, music, personalized ads, and social media
sentiment mining to name a few.
With these advancements in machine learning and artificial
intelligence that seem mind-boggling, TensorFlow is tool that
is helping to achieve these goals
35

36. Ressources
36
➢ TensorFlow tutorials
➢ quora.com/topic/TensorFlow-software-library
➢ Machine learning crash course
➢ Your first TensorFlow programming with Jupyter
➢ TensorFlow Dev-Summit 2018

37. Question ?
37
What is a tensor in TensorFlow?
➢ 1) : a generalization of vectors and Matrices to potentially higher
dimensions ?
➢ 2) : common programming model for parallel computing ?

38. 38
Thanks!
Any questions?

You can find me at rebai.ahmed@outlook.com