|
@@ -100,4 +100,35 @@
|
|
|
keywords = {Numerical Analysis (math.NA), FOS: Mathematics, FOS: Mathematics},
|
|
|
}
|
|
|
|
|
|
+@Book{Goodfellow-et-al-2016,
|
|
|
+ author = {Ian Goodfellow and Yoshua Bengio and Aaron Courville},
|
|
|
+ publisher = {MIT Press},
|
|
|
+ title = {Deep Learning},
|
|
|
+ year = {2016},
|
|
|
+ note = {\url{http://www.deeplearningbook.org}},
|
|
|
+}
|
|
|
+
|
|
|
+@Article{Lagaris1997,
|
|
|
+ author = {Lagaris, I. E. and Likas, A. and Fotiadis, D. I.},
|
|
|
+ title = {Artificial Neural Networks for Solving Ordinary and Partial Differential Equations},
|
|
|
+ year = {1997},
|
|
|
+ copyright = {Assumed arXiv.org perpetual, non-exclusive license to distribute this article for submissions made before January 2004},
|
|
|
+ doi = {10.48550/ARXIV.PHYSICS/9705023},
|
|
|
+ keywords = {Computational Physics (physics.comp-ph), Cellular Automata and Lattice Gases (nlin.CG), Quantum Physics (quant-ph), FOS: Physical sciences, FOS: Physical sciences},
|
|
|
+}
|
|
|
+
|
|
|
+@Article{Hornik1989,
|
|
|
+ author = {Hornik, Kurt and Stinchcombe, Maxwell and White, Halbert},
|
|
|
+ journal = {Neural Networks},
|
|
|
+ title = {Multilayer feedforward networks are universal approximators},
|
|
|
+ year = {1989},
|
|
|
+ issn = {0893-6080},
|
|
|
+ month = jan,
|
|
|
+ number = {5},
|
|
|
+ pages = {359--366},
|
|
|
+ volume = {2},
|
|
|
+ doi = {10.1016/0893-6080(89)90020-8},
|
|
|
+ publisher = {Elsevier BV},
|
|
|
+}
|
|
|
+
|
|
|
@Comment{jabref-meta: databaseType:bibtex;}
|