Welcome to the second session on Feedforward Neural Networks.
In the previous session, you understood the architecture of neural networks and how it was inspired by the structure of the human brain. You also learnt about the working of an artificial neuron, the hyperparameters and parameters of neural networks and various simplifying assumptions.
In this session, you will learn how information flows in a neural network from the input layer to the output layer to enable the neural network to make a prediction. The information flow in this direction is often called feedforward. You will also learn how to assess the performance of a neural network.
In this session
The following topics will be covered:
- Information flow from the input layer to the output layer
- Regression and classification feedforward methods
- Working of neural networks
- Loss function
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
The in-video and in-content questions for this module are not graded. Note that graded questions are given in a separate segment titled ‘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 | |
| Questions With 2 Attempts | 10 | 5 |
| Questions With 1 Attempt | 10 | 0 |
People you will hear from in this session:
Subject matter expert
Professor, IIIT-Bangalore
G. Srinivasaraghavan, PhD is a Partner at Performance Engineering Associates. He has a PhD in Computer Science from the Indian Institute of Technology Kanpur and has over 18 years of industry experience. At Infosys Technologies, India’s premier IT firm, he was responsible for the delivery of large, performance-critical IT systems for Fortune 500 clients in the telecom, BFSI and logistics spaces. He has over a dozen published papers in several reputed international fora, including journal of Algorithms, International Journal on Computational Geometry and Applications and Foundations of Software Technolgy and Theoretical Computer Science. In his previous position he was Chief Technology Officer at Aztecsoft Ltd(now a part of Mindtree Ltd), where he brought about a radical, product-quality-focussed shift in the firm’s approach to quality assessment.
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.
Report an error