Regression of complex functions over the sphere using neural networksDifference of Activation Functions in Neural Networks in generalCost function for Ordinal Regression using neural networksAdvantages of monotonic activation functions over non-monotonic functions in neural networks?Are there neural networks packages that use complex numbers?Cost/loss functions for multi-tasking regression neural networksAdvantages of Recurrent Neural Networks over basic Artificial Neural NetworksRegression with Neural Networks in Tensorflow problemProperly using activation functions of neural networkGeneralized Regression Neural NetworksRecurrent Neural Networks Over Multiple Documents Over Time
Can I say "fingers" when referring to toes?
Limits and Infinite Integration by Parts
Does IPv6 have similar concept of network mask?
How do apertures which seem too large to physically fit work?
Fear of getting stuck on one programming language / technology that is not used in my country
Quoting Keynes in a lecture
What are some good ways to treat frozen vegetables such that they behave like fresh vegetables when stir frying them?
A social experiment. What is the worst that can happen?
Mimic lecturing on blackboard, facing audience
Is there an injective, monotonically increasing, strictly concave function from the reals, to the reals?
Does Doodling or Improvising on the Piano Have Any Benefits?
Is there a RAID 0 Equivalent for RAM?
Lowest total scrabble score
Does the Linux kernel need a file system to run?
Did arcade monitors have same pixel aspect ratio as TV sets?
Can disgust be a key component of horror?
Need help understanding what a natural log transformation is actually doing and why specific transformations are required for linear regression
Calculating total slots
How do you respond to a colleague from another team when they're wrongly expecting that you'll help them?
Are Captain Marvel's powers affected by Thanos' actions in Infinity War
Open a doc from terminal, but not by its name
15% tax on $7.5k earnings. Is that right?
Can the US President recognize Israel’s sovereignty over the Golan Heights for the USA or does that need an act of Congress?
Can a stoichiometric mixture of oxygen and methane exist as a liquid at standard pressure and some (low) temperature?
Regression of complex functions over the sphere using neural networks
Difference of Activation Functions in Neural Networks in generalCost function for Ordinal Regression using neural networksAdvantages of monotonic activation functions over non-monotonic functions in neural networks?Are there neural networks packages that use complex numbers?Cost/loss functions for multi-tasking regression neural networksAdvantages of Recurrent Neural Networks over basic Artificial Neural NetworksRegression with Neural Networks in Tensorflow problemProperly using activation functions of neural networkGeneralized Regression Neural NetworksRecurrent Neural Networks Over Multiple Documents Over Time
$begingroup$
I am kinda new to Neural Networks and I am currently learning using TensorFlow.
My problem involves functions : $f : S^2 to mathbbC^2$ with some additionnal properties, $S^2$ being the unit sphere of $mathbbR^3$. My goal is, from (relatively few) discretizations points of the function $f$, to interpolate it over the sphere (or a portion of the sphere).
As I said, $f$ cannot be any function, it has some special properties. Lets pretend I have a way to generate a whole collection of functions $f_1,dots,f_N$ satisfying those properties.
What I would like to do it the following :
- Training a Neural Network on $f_i$ with a pre-defined discretization pattern over $S^2$,
- Giving as input a discretization (not on the same pattern as the training one) of a function $f$ I want to interpolate,
- Getting the value at any point I want on $S^2$.
Is it possible ? If yes, how ?
Thank you.
neural-network tensorflow interpolation
New contributor
$endgroup$
add a comment |
$begingroup$
I am kinda new to Neural Networks and I am currently learning using TensorFlow.
My problem involves functions : $f : S^2 to mathbbC^2$ with some additionnal properties, $S^2$ being the unit sphere of $mathbbR^3$. My goal is, from (relatively few) discretizations points of the function $f$, to interpolate it over the sphere (or a portion of the sphere).
As I said, $f$ cannot be any function, it has some special properties. Lets pretend I have a way to generate a whole collection of functions $f_1,dots,f_N$ satisfying those properties.
What I would like to do it the following :
- Training a Neural Network on $f_i$ with a pre-defined discretization pattern over $S^2$,
- Giving as input a discretization (not on the same pattern as the training one) of a function $f$ I want to interpolate,
- Getting the value at any point I want on $S^2$.
Is it possible ? If yes, how ?
Thank you.
neural-network tensorflow interpolation
New contributor
$endgroup$
add a comment |
$begingroup$
I am kinda new to Neural Networks and I am currently learning using TensorFlow.
My problem involves functions : $f : S^2 to mathbbC^2$ with some additionnal properties, $S^2$ being the unit sphere of $mathbbR^3$. My goal is, from (relatively few) discretizations points of the function $f$, to interpolate it over the sphere (or a portion of the sphere).
As I said, $f$ cannot be any function, it has some special properties. Lets pretend I have a way to generate a whole collection of functions $f_1,dots,f_N$ satisfying those properties.
What I would like to do it the following :
- Training a Neural Network on $f_i$ with a pre-defined discretization pattern over $S^2$,
- Giving as input a discretization (not on the same pattern as the training one) of a function $f$ I want to interpolate,
- Getting the value at any point I want on $S^2$.
Is it possible ? If yes, how ?
Thank you.
neural-network tensorflow interpolation
New contributor
$endgroup$
I am kinda new to Neural Networks and I am currently learning using TensorFlow.
My problem involves functions : $f : S^2 to mathbbC^2$ with some additionnal properties, $S^2$ being the unit sphere of $mathbbR^3$. My goal is, from (relatively few) discretizations points of the function $f$, to interpolate it over the sphere (or a portion of the sphere).
As I said, $f$ cannot be any function, it has some special properties. Lets pretend I have a way to generate a whole collection of functions $f_1,dots,f_N$ satisfying those properties.
What I would like to do it the following :
- Training a Neural Network on $f_i$ with a pre-defined discretization pattern over $S^2$,
- Giving as input a discretization (not on the same pattern as the training one) of a function $f$ I want to interpolate,
- Getting the value at any point I want on $S^2$.
Is it possible ? If yes, how ?
Thank you.
neural-network tensorflow interpolation
neural-network tensorflow interpolation
New contributor
New contributor
New contributor
asked Mar 19 at 5:49
nicomezinicomezi
1011
1011
New contributor
New contributor
add a comment |
add a comment |
0
active
oldest
votes
Your Answer
StackExchange.ifUsing("editor", function ()
return StackExchange.using("mathjaxEditing", function ()
StackExchange.MarkdownEditor.creationCallbacks.add(function (editor, postfix)
StackExchange.mathjaxEditing.prepareWmdForMathJax(editor, postfix, [["$", "$"], ["\\(","\\)"]]);
);
);
, "mathjax-editing");
StackExchange.ready(function()
var channelOptions =
tags: "".split(" "),
id: "557"
;
initTagRenderer("".split(" "), "".split(" "), channelOptions);
StackExchange.using("externalEditor", function()
// Have to fire editor after snippets, if snippets enabled
if (StackExchange.settings.snippets.snippetsEnabled)
StackExchange.using("snippets", function()
createEditor();
);
else
createEditor();
);
function createEditor()
StackExchange.prepareEditor(
heartbeatType: 'answer',
autoActivateHeartbeat: false,
convertImagesToLinks: false,
noModals: true,
showLowRepImageUploadWarning: true,
reputationToPostImages: null,
bindNavPrevention: true,
postfix: "",
imageUploader:
brandingHtml: "Powered by u003ca class="icon-imgur-white" href="https://imgur.com/"u003eu003c/au003e",
contentPolicyHtml: "User contributions licensed under u003ca href="https://creativecommons.org/licenses/by-sa/3.0/"u003ecc by-sa 3.0 with attribution requiredu003c/au003e u003ca href="https://stackoverflow.com/legal/content-policy"u003e(content policy)u003c/au003e",
allowUrls: true
,
onDemand: true,
discardSelector: ".discard-answer"
,immediatelyShowMarkdownHelp:true
);
);
nicomezi is a new contributor. Be nice, and check out our Code of Conduct.
Sign up or log in
StackExchange.ready(function ()
StackExchange.helpers.onClickDraftSave('#login-link');
);
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
StackExchange.ready(
function ()
StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fdatascience.stackexchange.com%2fquestions%2f47583%2fregression-of-complex-functions-over-the-sphere-using-neural-networks%23new-answer', 'question_page');
);
Post as a guest
Required, but never shown
0
active
oldest
votes
0
active
oldest
votes
active
oldest
votes
active
oldest
votes
nicomezi is a new contributor. Be nice, and check out our Code of Conduct.
nicomezi is a new contributor. Be nice, and check out our Code of Conduct.
nicomezi is a new contributor. Be nice, and check out our Code of Conduct.
nicomezi is a new contributor. Be nice, and check out our Code of Conduct.
Thanks for contributing an answer to Data Science Stack Exchange!
- Please be sure to answer the question. Provide details and share your research!
But avoid …
- Asking for help, clarification, or responding to other answers.
- Making statements based on opinion; back them up with references or personal experience.
Use MathJax to format equations. MathJax reference.
To learn more, see our tips on writing great answers.
Sign up or log in
StackExchange.ready(function ()
StackExchange.helpers.onClickDraftSave('#login-link');
);
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
StackExchange.ready(
function ()
StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fdatascience.stackexchange.com%2fquestions%2f47583%2fregression-of-complex-functions-over-the-sphere-using-neural-networks%23new-answer', 'question_page');
);
Post as a guest
Required, but never shown
Sign up or log in
StackExchange.ready(function ()
StackExchange.helpers.onClickDraftSave('#login-link');
);
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
Sign up or log in
StackExchange.ready(function ()
StackExchange.helpers.onClickDraftSave('#login-link');
);
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
Sign up or log in
StackExchange.ready(function ()
StackExchange.helpers.onClickDraftSave('#login-link');
);
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown