Skip to main content

All Questions

5 questions with no upvoted or accepted answers
Filter by
Sorted by
Tagged with
8 votes
0 answers
686 views

The function space defined by deep neural nets

Given a deep net graph and the activation functions on the hidden vertices do we have a description of the function space spanned by it? (even if for some specific architectures and activation ...
gradstudent's user avatar
  • 2,246
3 votes
0 answers
115 views

Linearized NLS/GP around a soliton and the spectrum of the evolution operator

I apologize if this has been asked before but so far I haven't found it anywhere. Consider the Nonlinear Schrödinger equation with a potential (i.e. Gross- Pitaevskii) in $\mathbb{R}^{d}$ $$i\Psi_{t} =...
Taotology's user avatar
2 votes
0 answers
70 views

Multiexponential analysis of infection counts with errors

In the past, I have seen some decompositions of sums of exponential decays into components by the Padé-Laplace method: Apply the Laplace transform $${\frak L}(\sum_{i=1}^n a_i e^{k_i t}) = \sum_{i=1}^...
Douglas Zare's user avatar
1 vote
0 answers
85 views

Maximizing the integral of a transformation that depends on a neighborhood of values of the original function

I'm not an expert in analysis whatsoever, so I might be posing a well-established question, or even an unanswerable one. Also, any suggestion on changes that might make the problem better are welcome. ...
Juan Meleiro's user avatar
1 vote
0 answers
114 views

Spins in classical statistical mechanics

I'm reading Kupiainen's notes on the renormalization group and also caught my attention. Actually, this is something that often causes my some confusion. On page 43, in the section about Ginzburg-...
JustWannaKnow's user avatar