In short, Solver is a what-if analysis tool for optimization. It is an add-in licensed from Frontline Systems that has shipped with Excel for many years.
An objective function is a measure of how similar a prediction of a value and the actual value are. Usually, we are looking to find the set of parameters that lead to the smallest possible cost which would imply that your algorithm will perform well.
I. Korejo, S. Yang, K. Brohi, and Z.U.A.Khuhro. International Journal on Soft Computing, Artificial Intelligence and Applications (IJSCAI), 2 (2):
19(April 2013)
G. Varela, P. Caamaño, F. Orjales, Á. Deibe, F. López-Peña, and R. Duro. Neurocomputing, 132 (0):
54 - 67(2014)Innovations in Nature Inspired Optimization and Learning Methods Selected papers from the Third World Congress on Nature and Biologically Inspired Computing (NaBIC2011) Machines learning for Non-Linear Processing Selected papers from the 2011 International Conference on Non-Linear Speech Processing (NoLISP 2011).
N. Desai, and S. Bandyopadhyay. Energy, 34 (10):
1674 - 1686(2009)11th Conference on Process Integration, Modelling and Optimisation for Energy Saving and Pollution Reduction.
E.L.Pankratov, and E.A.Bulaeva. International Journal of Computational Science, Information Technology and Control Engineering (IJCSITCE), 2 (3):
17(July 2015)
C. Wei, J. Lee, Q. Liu, and T. Ma. (2018)cite arxiv:1810.05369Comment: version 2: title changed from originally Ön the Margin Theory of Feedforward Neural Networks". Substantial changes from old version of paper, including a new lower bound on NTK sample complexity version 3: reorganized NTK lower bound proof.