Why this course?

Description

Deep learning is a subfield of artificial intelligence technology, where various neural networks will process the information and give accurate predictions. In deep learning we can implement various frameworks like keras , tensor flow , pytorch in real time applications. Various neural networks include artificial neural network, recurrent neural network, convolutional neural network, long short term memory neural network along with various applications. Industrial Applications for deep learning includes the healthcare industry, banking sectors, and share market analysis.

Total Duration: 8 Hrs | Modules: 5 | Assignments: 5 | Projects – 10

Module 1:  Introduction to deep learning 

• Introduction to deep learning
• What is deep learning
• History of deep learning
• Importance of deep learning
• Define  neural networks and list various types of neural networks .
• Various industrial applications of deep learning

Module 2: artificial neural networks 

• Introduction to artificial neural networks 
• Architecture of artificial neural networks
• Pros and cons of ANN network
• Implementation of ANN for churn model prediction.

Module 3:  deep learning frameworks 

Key Learning Objectives:  This Module will introduce the participants the Overview of  various deep learning frameworks which includes tensorflow ,keras, pytorch.

Assignment 1: apply various initializers for a keras model.

 Lesson 1: keras and tensorflow

We need to learn about various initializers, constraints, regularizations, activation functions to create a deep learning model with the help of keras framework. 

Assignment 2:  list various constraints and regularizers.

Lesson 2: various constraints and regularizers implementations in keras deep learning model. 

Implement constraints and regularizers 

Assignment 3: what are various constraints how to implement them ?

 Lesson 3: activation functions 

Learn how to implement activation functions in keras framework.

Assignment 4 -    describe how to use the pytorch framework .

Lesson 4:  pytorch 

Implementation of pytorch library file with deep learning models .

Project -    a sample deep learning model creation using pytorch.

 

Module 4: deep learning algorithms 

Key Learning Objectives:

List all various deep learning algorithms .

Lesson 5:  various deep learning algorithms 

Importance of various deep learning algorithms along with its implementations.

 Lesson 6: applications 

Performance analysis for various input data using different deep learning algorithms.

Assignment 5 – implement lstm model for bitcoin price prediction 

 

Project - image recognition using CNN.    

Lesson 7: 

Define  RNN and give its application.

Assignment 6 – house hold estimation using RNN.

Lesson 8: tensorflow 

Face recognition using tensorflow.

 Lesson 9: human pose estimation and tracking using deep learning.

 

For Related courses

After completing the course, automatically e-certificate will be generated for the participants.

 

Software / Tools:  

anaconda navigator software tool :-https://www.anaconda.com/products/distribution