Deep Neural Networks (DNNs)
- (Harvard University - Joyce Yang)
- Overview
Deep neural networks (DNNs) are a type of machine learning algorithm that mimic the brain's information processing. They are made up of layers, including nodes and edges, that contain mathematical relationships.
DNNs have at least two layers of complexity and use sophisticated math modeling to process data. The goal of this technology is to simulate the activity of the human brain, and more specifically the recognition of patterns and the transmission of information between the different layers of neural connections.
DNNs are used in computer vision, natural language processing, and transfer learning. For example, in an image recognition task, the algorithm might learn to associate certain features in an image (such as the shape of an object or the color of an object) with the correct label (such as "dog" or "cat").
The "deep" in "deep learning" refers to the depth of the network's layers. Modern GPUs have enabled the one-layer networks of the 1960s and the two- to three-layer networks of the 1980s to blossom into the 10-, 15-, even 50-layer networks of today.
