Want to create interactive content? It’s easy in Genially!

Get started free

RETROFUTURE

abdelrazek

Created on October 29, 2022

Start designing with a free template

Discover more than 1500 professional designs like these:

Women's Presentation

Vintage Photo Album

Geniaflix Presentation

Shadow Presentation

Newspaper Presentation

Memories Presentation

Zen Presentation

Transcript

ARTIFICIALINTELEGENCE

TENSORFLOW

Start

whAt we talking about?

History of it

TensorFlow?

Its Progression

What it supports

Elaborarion

Pros and Cons

Live example

What is it made of

Programme aspect

Training the model

Preparing Data

Data collection

Uses of Tensorflow

The result

Tensor flow?

what is tensorflow?

DEFFINITION

WHAT IS IT?

TensorFlow is an open-source end-to-end platform for creating Machine Learning applications. It is a symbolic software library that uses dataflow and differentiable programming to perform various tasks focused on training and inference of deep neural networks.

History of TensorFlow

A couple of years ago, deep learning started to outperform all other machine learning algorithms when giving a massive amount of data. Google saw it could use these deep neural networks to improve its services. They built a Library called TensorFlow to let researchers and developers work together on an AI model. Once developed and scaled, it allows lots of people to use it.

EVOLOUTION OF TENSORFLOW

2018

2017

2019

TensorFlow 1.0 was released for machine learning in JavaScript.

Kubeflow is released for the operation and deployment of TensorFlow on Kubernetes.

TensorFlow 2.0 is released which adds a number of components to TensorFlow.

PROS OF TENSORFLOW

Scalable: TensorFlow is not limited to one specific device.

Open Source Platform: It is available free of cost to anyone who wants to work with this.

Graphs: TensorFlow has a better data visualization power than any other available library.

Debugging: TensorFlow has Tensorboard which allows easy debugging of nodes.

Parallelism: TensorFlow employs GPU and CPU systems for its functioning.

cons of tensorflow

No windows support: Windows has a very limited set of features for Windows users.

Slow: It is comparatively slower and less usable compared to its competing frameworks.

Architectural limitation: TensorFlow’s architecture allows only execution of models and doesn’t allow its training.

Dependency: Even though TensorFlow reduces the size of the program and makes it user-friendly, it adds a layer of complexity to it.

Frequent Updates: TensorFlow undergoes frequent updates making it overhead for a user to time to time uninstall and reinstall it

CAN YOU ELABORATE MORE?

How does it work. Why is it called TensorFlow. Where can i run it.

More info

Where can TensorFlow run?

Why is it called TensorFlow?

How TensorFlow Works?

TensorFlow is available on 64-bit Linux, MacOS, Windows, and mobile computing platforms including Android and iOS. Its flexible architecture allows for the easy deployment of computation

it is called TensorFlow because the tensor goes in it, flows through a list of operations, and then it comes out the other side.

In a nutshell, data moves through a graph by taking inputs as a multi-dimensional array called Tensor. It allows you to construct a flowchart of operations that can be performed on these inputs, which goes at one end and comes at the other end as output.

What programming interfaces support TensorFlow?

There currently exist two programming interfaces, in C++ and Python, that permit interaction with the TensorFlow back end.

TENSORFLOW COMPONENTS

gRAPHS

tENSOR

A tensor is a vector or matrix of n-dimensions that represents all types of data. All values in a tensor hold identical data type with a known shape.

TensorFlow makes use of a graph framework. The graph gathers and describes all the series computations done during the training.

TECHNICAL ELABORATION

THE TENSORFLOW PROGRAMMING MODEL

THE TENSORFLOW PROGRAMMING MODEL

machine learning algorithms are represented as a computational graph. A computational or dataflow graph is a form of directed graph where vertices or nodes describe operations, while edges represent data flowing between these operations.

live example

Coding Example using TENSORFLOW

The next codes perform 4 important steps:- 1- Collecting Data 2- Prepareing Data 3- Training the Model 4- Evaluating the Model

collecting Data

The data used in this Example is a list of car objects like this:

preparing data

When preparing for machine learning, it is always important to Remove the data you don't need. This can be done by iterating (looping over) your data with a Map function .

converting into tensors

To use TensorFlow, input data needs to be converted to tensor data:

training the model

After preparing the data, training comes along, the previous two steps with this one will iterate for a significant amount of times:

plot the result

Testing the final result and mesure the accuracy of the model

Most common uses of tensorflow

02 Text-Based applications

01 Voice/sound recognition

Further popular uses of TensorFlow are text based applications such as sentimental analysis (CRM, Social Media), Threat Detection (Social Media, Goverment) and Fraud Detection (Insurance, Finance)

One of the most well-known uses of TensorFlow are Sound based applications. With the proper data feed, neural networks are capable of understanding audio signals.

Most common uses of tensorflow

03 image recognition

05 Video detection

04 Time series

Mostly used by Social Media, Telecom and Handset Manufacturers, Face recognition, Image search, Motion Detection, Machine Vision and Photo Clustering can be used also in Automotive, Aviation and Healthcare industries. Image Recognition aims to recognize and identify people and objects in images as well as understanding the content and context.

TensorFlow neural networks also work on video data. This is mainly used in Motion Detection, Real-Time Thread Detection in Gaming, Security, Airports and UX/UI fields.

TensorFlow Time Series algorithms are used for analyzing time series data in order to extract meaningful statistics. They allow forecasting non-specific time periods in addition to generate alternative versions of the time series.

THANKS!