TY - JOUR
T1 - Deep Learning
T2 - Current State
AU - Salas, Joaquin
AU - De Barros Vidal, Flavio
AU - Martinez-Trinidad, Francisco
N1 - Publisher Copyright:
© 2003-2012 IEEE.
PY - 2019/12
Y1 - 2019/12
N2 - Deep learning, a derived from machine learning, has grown into widespread usage with applications as diverse as cancer detection, elephant spotting, and game development. The number of published studies shows an increasing interest by researchers because of its demonstrated ability to achieve high performance in the solution of complex problems, the wide availability of data and computing resources, and the groundbreaking development of effective algorithms. This paper reviews the current state of deep learning. It includes a revision of basic concepts, such as the operations of feed forward and backpropagation, the use of convolution to extract features, the role of the loss function, and the optimization and learning processes; the survey of main stream techniques, in particular convolutional, recurrent, recursive, deep belief, deep generative, generative adversarial, and variational auto-enconder neural networks; the description of an ample array of applications organized by the type of technique employed; and the discussion of some of its most intriguing open problems.
AB - Deep learning, a derived from machine learning, has grown into widespread usage with applications as diverse as cancer detection, elephant spotting, and game development. The number of published studies shows an increasing interest by researchers because of its demonstrated ability to achieve high performance in the solution of complex problems, the wide availability of data and computing resources, and the groundbreaking development of effective algorithms. This paper reviews the current state of deep learning. It includes a revision of basic concepts, such as the operations of feed forward and backpropagation, the use of convolution to extract features, the role of the loss function, and the optimization and learning processes; the survey of main stream techniques, in particular convolutional, recurrent, recursive, deep belief, deep generative, generative adversarial, and variational auto-enconder neural networks; the description of an ample array of applications organized by the type of technique employed; and the discussion of some of its most intriguing open problems.
KW - Applications of Deep Learning
KW - Convolutional Neural Networks
KW - Deep Generative Networks
KW - Recurrent Neural Networks
KW - Recursive Neural Networks
UR - http://www.scopus.com/inward/record.url?scp=85081640421&partnerID=8YFLogxK
U2 - 10.1109/TLA.2019.9011537
DO - 10.1109/TLA.2019.9011537
M3 - Artículo
AN - SCOPUS:85081640421
SN - 1548-0992
VL - 17
SP - 1925
EP - 1945
JO - IEEE Latin America Transactions
JF - IEEE Latin America Transactions
IS - 12
M1 - 9011537
ER -