mathematical optimization - Why aren't neural networks convex? -


unlike linear , logistic regression, anns cost functions not convex, , susceptible local optima. can provide intuition why case anns , why hypothesis cannot modified produce convex function?

i found sufficient explanation here:

https://stats.stackexchange.com/questions/106334/cost-function-of-neural-network-is-non-convex

basically since weights permutable across layers there multiple solutions minima achieve same results, , function cannot convex (or concave either).


Comments

Popular posts from this blog

Is there a better way to structure post methods in Class Based Views -

reflection - How to access the object-members of an object declaration in kotlin -

php - Doctrine Query Builder Error on Join: [Syntax Error] line 0, col 87: Error: Expected Literal, got 'JOIN' -