Deep Learning Neural Networks with TensorFlow

Focused View

EDUCBA Bridging the Gap

7:27:26

5 View

1 - Deep Learning Neural Networks with TensorFlow

1 - Overview of DLUT.mp4

09:03

2 - Scenario of Perceptron.mp4

16:29

3 - Creating Neural Network Using TensorFlow.mp4

10:49

4 - Perform Multiclass Classification.mp4

10:15

5 - Initializing the Model.mp4

12:40

6 - Initializing the Model Continued.mp4

14:24

7 - Image Processing Using CNN.mp4

14:48

8 - Convolution Intuition.mp4

12:14

9 - Classifying the Photos of Dogs and Cats.mp4

10:27

10 - Deep Learning Neural Networks and its Layers.mp4

12:26

11 - Listing Directories.mp4

12:45

12 - Import Image Data Generator.mp4

13:06

13 - Advance Concept of Transfer Learning Part 1.mp4

14:59

14 - Advance Concept of Transfer Learning Part 2.mp4

11:27

15 - Advance Concept of Transfer Learning Part 3.mp4

13:20

2 - Project On Tensorflow Face Mask Detection Application

16 - Introduction to Project.mp4

03:03

17 - Package Installation.mp4

10:56

18 - Load Data Pretrained Mode.mp4

09:47

19 - Train Model Fit Model.mp4

01:22

20 - Load Save Model.mp4

02:06

21 - Function to Predict.mp4

04:05

22 - Final Result.mp4

01:03

3 - Project on Tensorflow Implementing Linear Model with Python

23 - Introduction to Tensorflow with Python.mp4

12:22

24 - Installation of Tensorflow.mp4

11:36

25 - Basic Data Types for Tensorflow.mp4

12:23

26 - Implementing Simple Linear Model.mp4

06:21

27 - Creating a Python File.mp4

08:58

28 - Optimization of Variable.mp4

11:05

29 - Implementing the Constructor Variable.mp4

10:57

30 - Printing the Variable Result.mp4

05:57

31 - Naming the Variable.mp4

09:58

4 - Deep Learning Automatic Image Captioning For Social Media With Tensorflow

32 - Introduction to Course.mp4

05:26

33 - Import the Libraries.mp4

09:00

34 - Accessing the Caption Dataset for Training.mp4

05:22

35 - Accessing the Image DataSet for Trainingb.mp4

02:09

36 - Preprocessing the Text Data.mp4

10:48

37 - PreProcess and Load Captions Data.mp4

11:06

38 - Loading the Captions for Training and Test Data.mp4

04:14

39 - Preprocessing of Image Data.mp4

10:58

40 - Loading Features for Train and Test Dataset.mp4

08:55

41 - Text Tokenization and Sequence Text.mp4

10:32

42 - Data Generators.mp4

10:49

43 - Define the Model.mp4

03:27

44 - Evaluation of Model.mp4

08:48

45 - Test the Model.mp4

07:35

46 - Create Streamlit App.mp4

10:11

47 - Streamlit Prediction.mp4

05:45

48 - Test Streamlit App.mp4

02:34

49 - Deploy Streamlit on AWS EC2 Instance.mp4

08:36

Description

Master deep learning with TensorFlow through hands-on projects and advanced applications in our comprehensive course

What You'll Learn?

Gain a solid understanding of deep learning neural networks using TensorFlow.
Explore the fundamentals of perceptrons, initializing models, and performing multiclass classification.
Dive into advanced concepts, including convolutional neural networks (CNN) and transfer learning.
Apply knowledge through real-world projects, such as creating a face mask detection application and implementing a linear model with Python.
Develop skills in automatic image captioning for social media using TensorFlow, including text tokenization and sequence text processing.
Learn to deploy a Streamlit app on AWS EC2 for image captioning predictions.

Who is this for?

Anyone who wants to pass the TensorFlow Developer exam so they can join Google's Certificate Network and display their certificate and badges on their resume, GitHub, and social media platforms including LinkedIn, making it easy to share their level of TensorFlow expertise with the world

Aspiring data scientists and machine learning enthusiasts. Professionals seeking to enhance their skills in deep learning and TensorFlow.

Students and researchers interested in neural network applications. Anyone looking to build practical expertise in image processing and natural language processing with TensorFlow.

What You Need to Know?

Mac / Windows / Linux - all operating systems work with this course!

No previous TensorFlow knowledge required. Basic understanding of Machine Learning is helpful

Basic understanding of Python programming. Familiarity with machine learning concepts. Knowledge of neural networks fundamentals. Prior experience with TensorFlow is helpful but not mandatory.

More details

Description
Welcome to the "Deep Learning Neural Networks with TensorFlow" course! This comprehensive program is designed to equip you with the essential knowledge and hands-on skills required to navigate the exciting field of deep learning using TensorFlow.
Overview:
In this course, you will embark on a journey through the fundamentals and advanced concepts of deep learning neural networks. We'll start by providing you with a solid foundation, introducing the core principles of neural networks, including the scenario of Perceptron and the creation of neural networks using TensorFlow.
Hands-on Projects:
To enhance your learning experience, we have incorporated practical projects that allow you to apply your theoretical knowledge to real-world scenarios. The "Face Mask Detection Application" project in Section 2 and the "Implementing Linear Model with Python" project in Section 3 will provide you with valuable hands-on experience, reinforcing your understanding of TensorFlow.
Advanced Applications:
Our course goes beyond the basics, delving into advanced applications of deep learning. Section 4 explores the fascinating realm of automatic image captioning for social media using TensorFlow. You will learn to preprocess data, define complex models, and deploy applications, gaining practical insights into the cutting-edge capabilities of deep learning.
Why TensorFlow?
TensorFlow is a leading open-source deep learning framework, widely adopted for its flexibility, scalability, and extensive community support. Whether you're a beginner or an experienced professional, this course caters to learners of all levels, guiding you through the intricacies of deep learning with TensorFlow.
Get ready to unravel the mysteries of neural networks, develop practical skills, and unleash the power of TensorFlow in the dynamic field of deep learning. Join us on this exciting learning journey, and let's dive deep into the world of neural networks together!
Section 1: Deep Learning Neural Networks with TensorFlow
This section serves as an in-depth introduction to deep learning using TensorFlow. In Lecture 1, you'll receive an overview of the field, setting the stage for subsequent lectures. Lecture 2 delves into the scenario of Perceptron, providing foundational knowledge. Lectures 3 to 6 guide you through the practical aspects of creating neural networks, emphasizing model initialization and multiclass classification. Lecture 7 introduces the critical concept of image processing using Convolutional Neural Networks (CNN). Further, Lectures 8 to 15 explore advanced topics, including deep learning neural networks' layers and transfer learning.
Section 2: Project On TensorFlow: Face Mask Detection Application
This hands-on project section allows you to apply your theoretical knowledge to a real-world scenario. Lecture 16 introduces the Face Mask Detection Application project, and subsequent lectures provide a step-by-step guide on implementing the application. From package installation to loading and saving models, the section covers essential aspects of the project. Lecture 22 concludes the project by showcasing the final result, giving you practical experience in applying TensorFlow to solve a specific problem.
Section 3: Project on TensorFlow - Implementing Linear Model with Python
This practical section focuses on implementing a linear model using TensorFlow and Python. Beginning with an introduction to TensorFlow with Python in Lecture 23, the section covers the installation process and basic data types. Lectures 26 to 30 walk you through the step-by-step implementation of a simple linear model, including variable optimization and constructor implementation. The section concludes with lectures on naming variables and printing results, providing a comprehensive understanding of linear models.
Section 4: Deep Learning: Automatic Image Captioning For Social Media With TensorFlow
This advanced section is dedicated to automatic image captioning using TensorFlow, a cutting-edge application of deep learning. Lectures 32 to 47 guide you through every stage of the process, from importing libraries to deploying a Streamlit app on an AWS EC2 instance. The section covers preprocessing text and image data, defining and evaluating the model, and creating a practical application for image captioning. By the end of this section, you'll have a deep understanding of applying TensorFlow to complex tasks in the realm of image processing and natural language understanding.
Who this course is for:
Anyone who wants to pass the TensorFlow Developer exam so they can join Google's Certificate Network and display their certificate and badges on their resume, GitHub, and social media platforms including LinkedIn, making it easy to share their level of TensorFlow expertise with the world
Aspiring data scientists and machine learning enthusiasts. Professionals seeking to enhance their skills in deep learning and TensorFlow.
Students and researchers interested in neural network applications. Anyone looking to build practical expertise in image processing and natural language processing with TensorFlow.

User Reviews

Rating

average 0

Total votes0

Focused display

TensorFlow

Neural Networks

EDUCBA Bridging the Gap

Instructor's Courses

EDUCBA is a leading global provider of skill based education addressing the needs of 1,000,000+ members across 70+ Countries. Our unique step-by-step, online learning model along with amazing 5000+ courses and 500+ Learning Paths prepared by top-notch professionals from the Industry help participants achieve their goals successfully. All our training programs are Job oriented skill based programs demanded by the Industry. At EDUCBA, it is a matter of pride for us to make job oriented hands-on courses available to anyone, any time and anywhere. Therefore we ensure that you can enroll 24 hours a day, seven days a week, 365 days a year. Learn at a time and place, and pace that is of your choice. Plan your study to suit your convenience and schedule.

Udemy

View courses Udemy

Students take courses primarily to improve job-related skills.Some courses generate credit toward technical certification. Udemy has made a special effort to attract corporate trainers seeking to create coursework for employees of their company.