Welcome to the module on Convolutional Neural Networks.
Convolutional Neural Networks, or CNNs, are neural networks specialised to work with visual data, i.e. images and videos (though not restricted to them). They are very similar to the vanilla neural networks (multilayer perceptrons) – every neuron in one layer is connected to every neuron in the next layer, they follow the same general principles of forward and backpropagation, etc. However, there are certain features of CNNs that make them perform extremely well on image processing tasks.
By the end of this module, you will be able to understand the working principles of CNNs, compare various CNN architectures and be able to choose the right architecture for specific tasks. In transfer learning, you will learn to use large pre-trained networks for your own computer vision tasks. You will also be able to train CNNs using Python + Keras.
In this session
The first session covers the following topics:
- The need for a new type of architecture for images
- Reading digital images
- Understanding convolutions
- The structure and topology of convolutional neural networks
- Feature Maps
- Training the network
Prerequisites
There are no prerequisites for this session other than knowledge of the matrix multiplication and previous courses on Neural Networks and, 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 on 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 | |
| Questions with 2 Attempts | 10 | 5 |
| Questions with 1 Attempt | 10 | 0 |
People you will hear from in this session
Subject Matter Expert:
Gopalakrishnan Srinivasaraghavan
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