190 lines
7.3 KiB
Plaintext
190 lines
7.3 KiB
Plaintext
% $ biblatex auxiliary file $
|
||
% $ biblatex bbl format version 3.3 $
|
||
% Do not modify the above lines!
|
||
%
|
||
% This is an auxiliary file used by the 'biblatex' package.
|
||
% This file may safely be deleted. It will be recreated by
|
||
% biber as required.
|
||
%
|
||
\begingroup
|
||
\makeatletter
|
||
\@ifundefined{ver@biblatex.sty}
|
||
{\@latex@error
|
||
{Missing 'biblatex' package}
|
||
{The bibliography requires the 'biblatex' package.}
|
||
\aftergroup\endinput}
|
||
{}
|
||
\endgroup
|
||
|
||
|
||
\refsection{0}
|
||
\datalist[entry]{ynt/global//global/global/global}
|
||
\entry{convergence_lbfgs}{article}{}{}
|
||
\name{author}{2}{}{%
|
||
{{hash=3773c3d5aaf3636d59b5d646468683ae}{%
|
||
family={Liu},
|
||
familyi={L\bibinitperiod},
|
||
given={Dong\bibnamedelima C.},
|
||
giveni={D\bibinitperiod\bibinitdelim C\bibinitperiod}}}%
|
||
{{hash=88a342d927bf795b0d92af8a5613da31}{%
|
||
family={Nocedal},
|
||
familyi={N\bibinitperiod},
|
||
given={Jorge},
|
||
giveni={J\bibinitperiod}}}%
|
||
}
|
||
\strng{namehash}{016da99314d2fb9b907bb0a91cc52ecd}
|
||
\strng{fullhash}{016da99314d2fb9b907bb0a91cc52ecd}
|
||
\strng{fullhashraw}{016da99314d2fb9b907bb0a91cc52ecd}
|
||
\strng{bibnamehash}{016da99314d2fb9b907bb0a91cc52ecd}
|
||
\strng{authorbibnamehash}{016da99314d2fb9b907bb0a91cc52ecd}
|
||
\strng{authornamehash}{016da99314d2fb9b907bb0a91cc52ecd}
|
||
\strng{authorfullhash}{016da99314d2fb9b907bb0a91cc52ecd}
|
||
\strng{authorfullhashraw}{016da99314d2fb9b907bb0a91cc52ecd}
|
||
\field{sortinit}{1}
|
||
\field{sortinithash}{4f6aaa89bab872aa0999fec09ff8e98a}
|
||
\field{labelnamesource}{author}
|
||
\field{labeltitlesource}{title}
|
||
\field{journaltitle}{Mathematical Programming}
|
||
\field{month}{8}
|
||
\field{number}{1–3}
|
||
\field{title}{On the limited memory BFGS method for large scale optimization}
|
||
\field{volume}{45}
|
||
\field{year}{1989}
|
||
\field{pages}{503\bibrangedash 528}
|
||
\range{pages}{26}
|
||
\verb{doi}
|
||
\verb 10.1007/bf01589116
|
||
\endverb
|
||
\endentry
|
||
\entry{Dogleg}{inproceedings}{}{}
|
||
\name{author}{3}{}{%
|
||
{{hash=f8ef8253cc84bb120a25129626f9bf75}{%
|
||
family={Ampazis},
|
||
familyi={A\bibinitperiod},
|
||
given={N.},
|
||
giveni={N\bibinitperiod}}}%
|
||
{{hash=ca32e2eb0ff1d4baff79927c876e24bc}{%
|
||
family={Spirou},
|
||
familyi={S\bibinitperiod},
|
||
given={S.},
|
||
giveni={S\bibinitperiod}}}%
|
||
{{hash=8857a8a8805ecdaf2863ccf5ebb56be2}{%
|
||
family={Perantonis},
|
||
familyi={P\bibinitperiod},
|
||
given={S.},
|
||
giveni={S\bibinitperiod}}}%
|
||
}
|
||
\list{location}{1}{%
|
||
{Los Alamitos, CA, USA}%
|
||
}
|
||
\list{publisher}{1}{%
|
||
{IEEE Computer Society}%
|
||
}
|
||
\strng{namehash}{043d6ae890a3edd2e8dd411887d99c3c}
|
||
\strng{fullhash}{043d6ae890a3edd2e8dd411887d99c3c}
|
||
\strng{fullhashraw}{043d6ae890a3edd2e8dd411887d99c3c}
|
||
\strng{bibnamehash}{043d6ae890a3edd2e8dd411887d99c3c}
|
||
\strng{authorbibnamehash}{043d6ae890a3edd2e8dd411887d99c3c}
|
||
\strng{authornamehash}{043d6ae890a3edd2e8dd411887d99c3c}
|
||
\strng{authorfullhash}{043d6ae890a3edd2e8dd411887d99c3c}
|
||
\strng{authorfullhashraw}{043d6ae890a3edd2e8dd411887d99c3c}
|
||
\field{sortinit}{2}
|
||
\field{sortinithash}{8b555b3791beccb63322c22f3320aa9a}
|
||
\field{labelnamesource}{author}
|
||
\field{labeltitlesource}{title}
|
||
\field{abstract}{In this paper, we introduce an advanced optimization algorithm for training feedforward neural networks. The algorithm combines the BFGS Hessian update formula with a special case of trust region techniques, called the Dogleg method, as an altenative technique to line search methods. Simulations regarding classification and function approximation problems are presented which reveal a clear improvement both in convergence and success rates over standard BFGS implementations.}
|
||
\field{booktitle}{Neural Networks, IEEE - INNS - ENNS International Joint Conference on}
|
||
\field{issn}{1098-7576}
|
||
\field{month}{7}
|
||
\field{title}{Training Feedforward Neural Networks with the Dogleg Method and BFGS Hessian Updates}
|
||
\field{volume}{2}
|
||
\field{year}{2000}
|
||
\field{pages}{1138}
|
||
\range{pages}{1}
|
||
\verb{doi}
|
||
\verb 10.1109/IJCNN.2000.857827
|
||
\endverb
|
||
\verb{urlraw}
|
||
\verb https://doi.ieeecomputersociety.org/10.1109/IJCNN.2000.857827
|
||
\endverb
|
||
\verb{url}
|
||
\verb https://doi.ieeecomputersociety.org/10.1109/IJCNN.2000.857827
|
||
\endverb
|
||
\endentry
|
||
\entry{Numerical-Optimization-2006}{book}{}{}
|
||
\name{author}{2}{}{%
|
||
{{hash=88a342d927bf795b0d92af8a5613da31}{%
|
||
family={Nocedal},
|
||
familyi={N\bibinitperiod},
|
||
given={Jorge},
|
||
giveni={J\bibinitperiod}}}%
|
||
{{hash=c49efb16d3fa7eef002cc3620d42ab8a}{%
|
||
family={Wright},
|
||
familyi={W\bibinitperiod},
|
||
given={Stephen\bibnamedelima J.},
|
||
giveni={S\bibinitperiod\bibinitdelim J\bibinitperiod}}}%
|
||
}
|
||
\list{location}{1}{%
|
||
{New York, NY, USA}%
|
||
}
|
||
\list{publisher}{1}{%
|
||
{Springer}%
|
||
}
|
||
\strng{namehash}{5b8fd28f6245ae8b0af119560622fa4f}
|
||
\strng{fullhash}{5b8fd28f6245ae8b0af119560622fa4f}
|
||
\strng{fullhashraw}{5b8fd28f6245ae8b0af119560622fa4f}
|
||
\strng{bibnamehash}{5b8fd28f6245ae8b0af119560622fa4f}
|
||
\strng{authorbibnamehash}{5b8fd28f6245ae8b0af119560622fa4f}
|
||
\strng{authornamehash}{5b8fd28f6245ae8b0af119560622fa4f}
|
||
\strng{authorfullhash}{5b8fd28f6245ae8b0af119560622fa4f}
|
||
\strng{authorfullhashraw}{5b8fd28f6245ae8b0af119560622fa4f}
|
||
\field{sortinit}{2}
|
||
\field{sortinithash}{8b555b3791beccb63322c22f3320aa9a}
|
||
\field{labelnamesource}{author}
|
||
\field{labeltitlesource}{title}
|
||
\field{edition}{2e}
|
||
\field{title}{Numerical Optimization}
|
||
\field{year}{2006}
|
||
\endentry
|
||
\entry{BenchmarkTools}{article}{}{}
|
||
\name{author}{2}{}{%
|
||
{{hash=69bd6c70a08a67d2841abb1b24a5ccfa}{%
|
||
family={{Chen}},
|
||
familyi={C\bibinitperiod},
|
||
given={Jiahao},
|
||
giveni={J\bibinitperiod}}}%
|
||
{{hash=d8a5df654714218c1b828ffab66545f1}{%
|
||
family={{Revels}},
|
||
familyi={R\bibinitperiod},
|
||
given={Jarrett},
|
||
giveni={J\bibinitperiod}}}%
|
||
}
|
||
\strng{namehash}{9162f41ecdba576d7faa1a6d6e27bc25}
|
||
\strng{fullhash}{9162f41ecdba576d7faa1a6d6e27bc25}
|
||
\strng{fullhashraw}{9162f41ecdba576d7faa1a6d6e27bc25}
|
||
\strng{bibnamehash}{9162f41ecdba576d7faa1a6d6e27bc25}
|
||
\strng{authorbibnamehash}{9162f41ecdba576d7faa1a6d6e27bc25}
|
||
\strng{authornamehash}{9162f41ecdba576d7faa1a6d6e27bc25}
|
||
\strng{authorfullhash}{9162f41ecdba576d7faa1a6d6e27bc25}
|
||
\strng{authorfullhashraw}{9162f41ecdba576d7faa1a6d6e27bc25}
|
||
\field{sortinit}{2}
|
||
\field{sortinithash}{8b555b3791beccb63322c22f3320aa9a}
|
||
\field{labelnamesource}{author}
|
||
\field{labeltitlesource}{title}
|
||
\field{eid}{arXiv:1608.04295}
|
||
\field{eprintclass}{cs.PF}
|
||
\field{eprinttype}{arXiv}
|
||
\field{journaltitle}{arXiv e-prints}
|
||
\field{month}{8}
|
||
\field{title}{{Robust benchmarking in noisy environments}}
|
||
\field{year}{2016}
|
||
\verb{eprint}
|
||
\verb 1608.04295
|
||
\endverb
|
||
\keyw{Computer Science - Performance,68N30,B.8.1,D.2.5}
|
||
\endentry
|
||
\enddatalist
|
||
\endrefsection
|
||
\endinput
|
||
|