Convolutional Neural Network

Convolutional Neural Network (pronunciation: /kɒnvəˈljuːʃənəl ˈnjuːrəl ˈnɛtwɜːrk/) is a type of Artificial Neural Network designed to process data with a grid-like topology, such as an image. The term "convolutional" refers to the mathematical operation the network performs.

Etymology

The term "Convolutional Neural Network" originates from the mathematical term "convolution", which is a mathematical operation on two functions that produces a third function. The term "neural network" is derived from its resemblance to a network of neurons in a brain.

Related Terms

• Artificial Neural Network
• Deep Learning
• Machine Learning
• Artificial Intelligence
• Backpropagation
• ReLU
• Softmax Function
• Loss Function
• Gradient Descent

Description

A Convolutional Neural Network (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. The pre-processing required in a CNN is much lower as compared to other classification algorithms. While in primitive methods filters are hand-engineered, with enough training, CNNs have the ability to learn these filters/characteristics.

The architecture of a CNN is designed to take advantage of the 2D structure of an input image (or other 2D input such as a speech signal). This is achieved with local connections and tied weights followed by some form of pooling which results in translation invariant features. Another benefit of CNNs is that they are easier to train and have many fewer parameters than fully connected networks with the same number of hidden units.

See Also

• Artificial Neural Network
• Deep Learning
• Machine Learning
• Artificial Intelligence

This WikiMD.org article is a stub. You can help make it a full article.