Convolutional Neural Networks (CNNs)

Introduction

Deep Learning – which has emerged as an effective tool for analyzing big data – uses complex algorithms and artificial neural networks to train machines/computers so that they can learn from experience, classify and recognize data/images just like a human brain does. Within Deep Learning, a Convolutional Neural Network or CNN is a type of artificial neural network, which is widely used for image/object recognition and classification. Deep Learning thus recognizes objects in an image by using a CNN. CNNs are playing a major role in diverse tasks/functions like image processing problems, computer vision tasks like localization and segmentation, video analysis, to recognize obstacles in self-driving cars, as well as speech recognition in natural language processing. As CNNs are playing a significant role in these fast-growing and emerging areas, they are very popular in Deep Learning.

Brain’s Architecture Inspired CNNs

A typical neural network will have an input layer, hidden layers, and an output layer. CNNs are inspired by the architecture of the brain. Just like a neuron in the brain processes and transmits information throughout the body, artificial neurons or nodes in CNNs take inputs, processes them and sends the result as output. The image is fed as input. The input layer accepts the image pixels as input in the form of arrays. In CNNs, there could be multiple hidden layers, which perform feature extraction from the image by doing calculations. This could include convolution, pooling, rectified linear units, and fully connected layers. Convolution is the first layer that does feature extraction from an input image. The fully connected layer classifies the object and identifies it in the output layer. “CNNs are feedforward networks in that information flow takes place in one direction only, from their inputs to their outputs. Just as artificial neural networks (ANN) are biologically inspired, so are CNNs. The visual cortex in the brain, which consists of alternating layers of simple and complex cells, motivates their architecture. CNN architectures come in several variations; however, in general, they consist of convolutional and pooling (or subsampling) layers, which are grouped into modules. Either one or more fully connected layers, as in a standard feedforward neural network, follow these modules,” describes a paper on “Deep Convolutional Neural Networks for Image Classification: A Comprehensive Review”, in the journal ‘Neural Computation’, which is published by MIT Press.

A Potent Tool Within Deep Learning

• CNNs have fundamentally changed our approach towards image recognition as they can detect patterns and make sense of them. They are considered the most effective architecture for image classification, retrieval and detection tasks as the accuracy of their results is very high.

• They have broad applications in real-world tests, where they produce high-quality results and can do a good job of localizing and identifying where in an image a person/car/bird, etc., are. This aspect has made them the go-to method for predictions involving any image as an input.

• A critical feature of CNNs is their ability to achieve ‘spatial invariance’, which implies that they can learn to recognize and extract image features anywhere in the image. There is no need for manual extraction as CNNs learn features by themselves from the image/data and perform extraction directly from images. This makes CNNs a potent tool within Deep Learning for getting accurate results.

• According to the paper published in ‘Neural Computation’, “the purpose of the pooling layers is to reduce the spatial resolution of the feature maps and thus achieve spatial invariance to input distortions and translations.” As the pooling layer brings down the number of parameters needed to process the image, processing becomes faster even as it reduces memory requirement and computational cost.

• While image analysis has been the most widespread use of CNNs, they can also be used for other data analysis and classification problems. Therefore, they can be applied across a diverse range of sectors to get precise results, covering critical aspects like face recognition, video classification, street/traffic sign recognition, classification of galaxy and interpretation and diagnosis/analysis of medical images, among others.