Also found in: Dictionary, Thesaurus, Medical, Acronyms, Idioms, Wikipedia.
deep learningDeep learning is an advanced type of machine learning architecture employed by neural networks, most commonly by "convolutional neural networks." Deep learning is used in applications such as computer vision, self-driving cars, natural language processing and online advertising. For example, deep learning enables facial recognition to be more accurate, and it allows medical scans to be interpreted without human analysis.
In the training phase of a deep learning model, thousands of images of similar objects, such as a car, truck, horse or human being, are input as examples. The image is divided into pixels that are connected to several layers, each layer identifying a different block of pixels. By the time the image reaches the final layer, the input pattern has been identified. These are the so-called "hidden layers" between the input and output of a deep learning model. See convolutional neural network.
The deep learning phase turns the neural network into the "inference engine," which does the actual processing such as identifying an object or making a decision. The greater number of layers in the training phase, the more accurate the inference engine and the better the results. See DLA, AI, machine learning, GAN, neural network and TensorFlow.
|Algorithms Make Mistakes|
|Deep learning algorithms can be fooled. A famous example is mistaking a muffin for a puppy. Like a CAPTCHA, this verification test is used to ensure the viewer is human and not a bot, and images such as these can confuse an algorithm (see CAPTCHA).|
|Deep Learning in the Hierarchy|
|Deep learning is a subset within machine learning, which is a major category of artificial intelligence (AI).|
downlink(1) The transmission from a satellite down to an earth station. Contrast with uplink.
(2) The transmission from a cell tower to a cellphone or other mobile device. Contrast with uplink.
downloadTo transmit a file over a network. In a communications session, "download" and "upload" imply a remote/local scenario, in which data are being downloaded from the "remote" server into the user's "local" computer. Uploading is the reverse.
The time it takes to download depends on file size and network speed. Via analog dial-up modems, Web pages take several seconds, and a 10MB file can take an hour. DSL, cable and FiOS are from 15 to 600 times faster, reaching the same speed as downloading from a server within the local network (LAN). See Internet speed.
From the Internet
Downloading images, articles and applications from the Internet is no more than "Click Here" on a Web page. The only thing users must know is what to do with the downloaded file. If the download is an app, it must be installed, which can happen automatically or require the user to take one more step. See download vs. upload, download protocol and client download.
From the Local Network (LAN)
In a server in a private network, files are placed in sharable folders that can be downloaded to users' computers. Using a file manager, such as Explorer in Windows or Finder in Mac, users can locate the files by computer and folder name. See file manager.
From Computer to Mobile Devices
Transferring files to a smartphone or tablet plugged into the USB port of a computer is more a copy function than a download. The mobile device appears as a storage drive to the computer.
dual layerTypically refers to optical media that contain two layers on a single side in order to double or nearly double the storage capacity. Also called "double layer." See DVD-9 and Blu-ray.
Copyright © 1981-2019 by The Computer Language Company Inc. All Rights reserved. THIS DEFINITION IS FOR PERSONAL USE ONLY. All other reproduction is strictly prohibited without permission from the publisher.
1. On drawings, abbr. for dead load.
2. On drawings, abbr. for deadlight.
McGraw-Hill Dictionary of Architecture and Construction. Copyright © 2003 by McGraw-Hill Companies, Inc.