Ggthjy

Lightning Data Table inline edit

What's the oldest plausible frozen specimen for a Jurassic Park style story-line?

Critique vs nitpicking

How vim overwrites readonly mode?

How to completely remove a package in Ubuntu (like it never existed)

Can you determine if focus is sharp without diopter adjustment if your sight is imperfect?

A fantasy book with seven white haired women on the cover

Eww, those bytes are gross

Is there any advantage in specifying './' in a for loop using a glob?

Non-Cancer terminal illness that can affect young (age 10-13) girls?

Why is it that Bernie Sanders is always called a "socialist"?

Cat is tipping over bed-side lamps during the night

Can a player sacrifice a creature after declaring that creature as blocker while taking lethal damage?

Am I correct in stating that the study of topology is purely theoretical?

Is there a way to not have to poll the UART of an AVR?

A question about partitioning positivie integers into finitely many arithmetic progresions

Charging phone battery with a lower voltage, coming from a bike charger?

How is this property called for mod?

What is the industry term for house wiring diagrams?

Crack the bank account's password!

hrule into tikz circle node

Can my friend and I spend the summer in Canada (6 weeks) at 16 years old without an adult?

Reading Mishnayos without understanding

Taking headphones when quitting job

Proper order of optimizing hyperparameters in ANN

Is there a thumb-rule for designing neural-networks?When to use what - Machine LearningWhy does applying PCA on targets causes underfitting?Deep Learning: Feed Forward for Unbalanced Classes Using Tensor FlowBounds for MLP hyperparameter searchRecurrent neural network producing same predictionsANN Variable CorrelationNeural network only converges when data cloud is close to 0How does one interpret output from hyper-engine while optimizing a single hyperparameter of a neural network?What kinds of math do I need to know to construct graph that preserve its directed simplicies at each time step?Improve model performance on unseen data

0

$begingroup$

I have built a neural network for approximating a certain function and decided on a metric how to evaluate the performance. Now, where do I start with optimizing to get the optimal result? I need to decide on number of layers, hidden neurons, learning rate, learning algorithms and all other hyperparameters. What is the usual procedure and order in which to optimize all network's parameters? I guess I am looking for some kind of general guidelines to follow to obtain the best possible performance

machine-learning neural-network

share|improve this question

asked 4 hours ago

GuestGuest

1

New contributor

Guest is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.

$endgroup$

• 
  
  
  

  
  1
  

  
  
  
  
  
  

  
  $begingroup$
  Possible duplicate of Is there a thumb-rule for designing neural-networks?
  $endgroup$
  – João Almeida
  3 hours ago
  

  
  
  
  

add a comment | 

0

$begingroup$

I have built a neural network for approximating a certain function and decided on a metric how to evaluate the performance. Now, where do I start with optimizing to get the optimal result? I need to decide on number of layers, hidden neurons, learning rate, learning algorithms and all other hyperparameters. What is the usual procedure and order in which to optimize all network's parameters? I guess I am looking for some kind of general guidelines to follow to obtain the best possible performance

machine-learning neural-network

share|improve this question

asked 4 hours ago

GuestGuest

1

New contributor

Guest is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.

$endgroup$

• 
  
  
  

  
  1
  

  
  
  
  
  
  

  
  $begingroup$
  Possible duplicate of Is there a thumb-rule for designing neural-networks?
  $endgroup$
  – João Almeida
  3 hours ago
  

  
  
  
  

add a comment | 

$begingroup$

I have built a neural network for approximating a certain function and decided on a metric how to evaluate the performance. Now, where do I start with optimizing to get the optimal result? I need to decide on number of layers, hidden neurons, learning rate, learning algorithms and all other hyperparameters. What is the usual procedure and order in which to optimize all network's parameters? I guess I am looking for some kind of general guidelines to follow to obtain the best possible performance

machine-learning neural-network

share|improve this question

asked 4 hours ago

GuestGuest

1

New contributor

Guest is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.

$endgroup$

share|improve this question

asked 4 hours ago

GuestGuest

1

New contributor

Guest is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.

share|improve this question

asked 4 hours ago

GuestGuest

1

New contributor

Guest is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.

asked 4 hours ago

GuestGuest

1

New contributor

Guest is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.

asked 4 hours ago

GuestGuest

1

1 Answer
1

active

oldest

votes

0

$begingroup$

My initial suggestion is to look in the literature for networks which have been implemented to do solve similar problems and start from there.
Then you should just try a bunch of different values for the parameters and see what works in your case.

See also this Cross Validated question: https://stats.stackexchange.com/questions/181/how-to-choose-the-number-of-hidden-layers-and-nodes-in-a-feedforward-neural-netw

share|improve this answer

answered 2 hours ago

João AlmeidaJoão Almeida

29117

$endgroup$

add a comment | 

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
});


}
});

Guest is a new contributor. Be nice, and check out our Code of Conduct.

draft saved

draft discarded

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

Name

Email

Required, but never shown

StackExchange.ready(
function () {
StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fdatascience.stackexchange.com%2fquestions%2f46208%2fproper-order-of-optimizing-hyperparameters-in-ann%23new-answer', 'question_page');
}
);

Post as a guest

Name

Email

Required, but never shown

0

$begingroup$

My initial suggestion is to look in the literature for networks which have been implemented to do solve similar problems and start from there.
Then you should just try a bunch of different values for the parameters and see what works in your case.

See also this Cross Validated question: https://stats.stackexchange.com/questions/181/how-to-choose-the-number-of-hidden-layers-and-nodes-in-a-feedforward-neural-netw

share|improve this answer

answered 2 hours ago

João AlmeidaJoão Almeida

29117

$endgroup$

add a comment | 

0

$begingroup$

My initial suggestion is to look in the literature for networks which have been implemented to do solve similar problems and start from there.
Then you should just try a bunch of different values for the parameters and see what works in your case.

See also this Cross Validated question: https://stats.stackexchange.com/questions/181/how-to-choose-the-number-of-hidden-layers-and-nodes-in-a-feedforward-neural-netw

share|improve this answer

answered 2 hours ago

João AlmeidaJoão Almeida

29117

$endgroup$

add a comment | 

$begingroup$

My initial suggestion is to look in the literature for networks which have been implemented to do solve similar problems and start from there.
Then you should just try a bunch of different values for the parameters and see what works in your case.

See also this Cross Validated question: https://stats.stackexchange.com/questions/181/how-to-choose-the-number-of-hidden-layers-and-nodes-in-a-feedforward-neural-netw

share|improve this answer

answered 2 hours ago

João AlmeidaJoão Almeida

29117

$endgroup$

share|improve this answer

answered 2 hours ago

João AlmeidaJoão Almeida

29117

answered 2 hours ago

João AlmeidaJoão Almeida

29117

answered 2 hours ago

João AlmeidaJoão Almeida

29117