Convolutional Neural Networks use a deep learning algorithm to efficiently process information.

Benefits

  • Increased efficiency
  • Increased accuracy
  • Decreased processing time

Applications

  • Artificial Intelligence
  • Machine learning

UN Sustainable Development Goals Addressed

  • Goal 9: Industry Innovation & Infrastructure

The Challenge

Computers are capable of processing a lot information faster than humans can. However, when it comes to visual information, computers slow down to process the breadth and variety of information presented in an image. The computer needs to keep track of the information, creating a lot of storage and using a lot of computing power.

Innovation Details

A Convolutional Neural Network is an algorithm that takes an input image, assigns importance to various aspects of the image, and then can differentiate between the aspects within the image, similar to the human visual processing system. The entire computer system is able to identify what is in the image because the levels of importance become features on a map that the computer recognizes. This system can then thoroughly process the entire image without creating a large amount of extra data.

Image: Grace W. Lindsay / arXiv / Copyright © - All rights reserved

The relationship between components of the visual system and the base operations of a convolutional neural network. Photo: Grace W. Lindsay/University College London.

Biological Model

The human visual system is comprised of several different types of cells. Simple cells have have ‘preferred locations’ on the image, meaning they respond most strongly to certain types of inputs (for example, a line at a particular angle). Complex cells receive input from many simple cells and thus have more spatially invariant responses. These operations are replicated in a convolutional neural network.