deep learning
643 Views

GC: n

CT: Deep learning allows computational models that are composed of multiple processing layers to learn representations of data with multiple levels of abstraction. These methods have dramatically improved the state-of-the-art in speech recognition, visual object recognition, object detection and many other domains such as drug discovery and genomics.

S: UCSC – https://goo.gl/L1e2d2 (last access: 9 January 2019).

N: 1. – deep (adj): From Old English deop “having considerable extension downward,” especially as measured from the top or surface, also figuratively, “profound, awful, mysterious; serious, solemn,” from Proto-Germanic *deupaz (source also of Old Saxon diop, Old Frisian diap, Dutch diep, Old High German tiof, German tief, Old Norse djupr, Danish dyb, Swedish djup, Gothic diups “deep”).
– learning (n): Old English leornung “study, action of acquiring knowledge,” verbal noun from leornian. Meaning “knowledge acquired by systematic study, extensive literary and scientific culture” is from mid-14c.
2. Aspect of artificial intelligence (AI) that is concerned with emulating the learning approach that human beings use to gain certain types of knowledge.
3. Deep-learning methods are representation-learning methods with multiple levels of representation, obtained by composing simple but non-linear modules that each transform the representation at one level (starting with the raw input) into a representation at a higher, slightly more abstract level. With the composition of enough such transformations, very complex functions can be learned.
4. Note that sometimes the deep learning is about learning with deep architectures for signal and information processing. It is not about deep understanding of the signal or information, although in many cases they may be related.
5. The key aspect of deep learning is that these layers of features are not designed by human engineers: they are learned from data using a general-purpose learning procedure.
6. Classification tasks: Higher layers of representation amplify aspects of the input that are important for discrimination and suppress irrelevant variations.

  • An image, for example, comes in the form of an array of pixel values, and the learned features in the first layer of representation typically represent the presence or absence of edges at particular orientations and locations in the image.
  • The second layer typically detects motifs by spotting particular arrangements of edges, regardless of small variations in the edge positions.
  • The third layer may assemble motifs into larger combinations that correspond to parts of familiar objects, and subsequent layers would detect objects as combinations of these parts.
  • The key aspect of deep learning is that these layers of features are not designed by human engineers: they are learned from data using a general-purpose learning procedure.

S: 1. OED – https://goo.gl/QCM1He; https://goo.gl/Z8bxk2 (last access: 9 January 2019). 2. TechT – https://goo.gl/QDLxQJ (last access: 9 January 2019). 3. UCSC – https://goo.gl/L1e2d2 (last access: 9 January 2019). 4. NOW – file:///Users/rodrigorivera/Downloads/9781601988157-summary.pdf (last access: 9 January 2019). 5 & 6. UCSC – https://goo.gl/L1e2d2 (last access: 9 January 2019).

SYN:
S:

CR: artificial intelligence, cognition , cognitive science, computational intelligence, computer science, e-learning, intelligent agent, intelligent system, machine learning, semantic network, virtual personal assistant.