In the previous module on Introduction to Neural Networks – Part 1, you learnt how information flows through a neural network in the forward direction.
In this Module
In this module, you will learn how to train a neural network using backpropagation, apply different optimisation techniques, perform hyperparameter tuning etc. You will also learn the practical aspects of training large neural networks.
In this Session
In this session, you will learn about the process of training neural networks, which is called backpropagation.
Here, the following topics will be covered:
- Gradient descent in neural networks
- Backpropagation algorithm
- Introduction to TensorFlow
- Implementation of a neural network using TensorFlow
Prerequisites
As the main prerequisites for this session, you must have a basic understanding of the concepts of vectors, matrix multiplication, derivatives and partial derivatives and must have completed the previous courses on statistics and ML.
Guidelines for in-module questions
During the session, there will be small coding challenges that you can attempt in order to become fluent with TensorFlow.
The in-video and in-content questions for this module are not graded. Note that graded questions are given in a separate segment labelled ‘Graded Questions’ at the end of this session. The graded questions in this session will adhere to the following guidelines.
First Attempt Marks | Second Attempt Marks | |
Question With 2 Attempts | 10 | 5 |
Question With 1 Attempt | 10 | 0 |
People you will hear from in this session
Subject Matter Expert
Gunnvant is experienced analytics professional with a demonstrated history of working in EdTech. He has designed and helped launch machine learning, data science, and deep learning training programs for learners with varied skillsets and different career expectations. He has also been involved in tech advocacy.
Dr Avishek Pal
Senior Data Scientist at Microsoft
Avishek has more than 12 years of experience in the data science and software industry and has worked for companies such as IBM, Ericsson and Fidelity Investments. He completed his PhD in Industrial and Systems Engineering from the University of Warwick, UK. Avishek’s current work at Microsoft includes mining massive data sets to generate rich content to improve the local search experience on Bing for Great Britain, France, Germany, Austria and India. He leads the India time zone of the Microsoft WorldWide ML community.
Report an error