Welcome to the session on CNN Architectures and Transfer Learning.
In the previous session, you had analysed the architecture of VGGNet in detail. In this session, you will study some other famous architectures which had achieved significantly better performance in the ImageNet competition over their predecessors. Specifically, you will study the architectures of AlexNet, GoogleNet and ResNet.
You will also learn to use these pre-trained models for your own problems using what is called Transfer Learning. Finally, we will conclude this session by analysing the performance (not just the accuracy, but efficiency as well) of various popular CNNs for practical deployment purposes, a study recently published in the paper ‘An analysis of Deep Neural Network Models for Practical Applications‘ by A Canziani.
In this Session
We will cover the following topics in this session:
- CNN architectures: AlexNet, GoogleNet, ResNet
- Transfer Learning
- Analysis of Deep Neural Network Models
Prerequisites
There are no prerequisites for this session other than knowledge of the matrix multiplication and the previous session on CNN architecture.
Guidelines for In-Module Questions
The in-video and in-content questions for this module are not graded. Note that graded questions are given on a separate page 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:
Professor, IIIT-Bangalore
The International Institute of Information Technology, Bangalore, commonly known as IIIT Bangalore, is a premier national graduate school in India. Founded in 1999, it offers Integrated M.Tech., M.Tech., M.S. (Research) and PhD programs in the field of Information Technology.
Report an error