Convolutional Neural Networks

What are convolutional neural networks?

A Convolutional Neural Network (ConvNet/CNN) is a Deep Learning algorithm which can take in an input image, assign importance (learnable weights and biases) to various aspects/objects in the image and be able to differentiate one from the other.

How do convolutional neural networks work?

A CNN takes in a large amount of image data and utilizes multi channeled images. Due to digital color images having red-blue green (RGB) encoding, a convolutional network ingests such images as three separate strata of color stacked one on top of the other. The depth layers in the three layers of colors(RGB) interpreted by CNNs are referred to as channels.

Layers in CNN

• Convolutional Layer: It is the main building block of CNN. It contains all the filters, parameters of which are to be learned throughout the training.

• Pooling Layer: It is used to reduce the number of parameters to learn and the computation performed in the network.

Fully-Connected (FC) Layer: It forms the last few layers of the network. The input to this layer is the output of the convolutional ot the pooling layer which is flattened and then fed into the fully connected layer.

Applications

• Face detection: CNN takes an image as the input and produces a set of values that represent characteristics of faces or facial features at different parts of the image.

• Facial emotion recognition: CNNS have been used to help distinguish between different facial expressions such as anger, sadness, or happiness.

Object detection: CNN has been applied to object recognition across images by classifying objects based on shapes and patterns found within an image.

. Other than the above mentioned, self driving cars, auto translation, next word prediction, x ray image analysis, cancer detection, etc