TY - CHAP
T1 - Why deep neural networks
T2 - A possible theoretical explanation
AU - Baral, Chitta
AU - Fuentes, Olac
AU - Kreinovich, Vladik
N1 - Publisher Copyright:
© Springer International Publishing AG 2018.
PY - 2018
Y1 - 2018
N2 - In the past, the most widely used neural networks were 3-layer ones. These networks were preferred, since one of the main advantages of the biological neural networks—which motivated the use of neural networks in computing—is their parallelism, and 3-layer networks provide the largest degree of parallelism. Recently, however, it was empirically shown that, in spite of this argument, multi-layer (“deep”) neural networks leads to a much more efficient machine learning. In this paper, we provide a possible theoretical explanation for the somewhat surprising empirical success of deep networks.
AB - In the past, the most widely used neural networks were 3-layer ones. These networks were preferred, since one of the main advantages of the biological neural networks—which motivated the use of neural networks in computing—is their parallelism, and 3-layer networks provide the largest degree of parallelism. Recently, however, it was empirically shown that, in spite of this argument, multi-layer (“deep”) neural networks leads to a much more efficient machine learning. In this paper, we provide a possible theoretical explanation for the somewhat surprising empirical success of deep networks.
UR - http://www.scopus.com/inward/record.url?scp=85029219978&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85029219978&partnerID=8YFLogxK
U2 - 10.1007/978-3-319-61753-4_1
DO - 10.1007/978-3-319-61753-4_1
M3 - Chapter
AN - SCOPUS:85029219978
T3 - Studies in Systems, Decision and Control
SP - 1
EP - 5
BT - Studies in Systems, Decision and Control
PB - Springer International Publishing
ER -