Are there neural networks with very few nodes that decently solve non-trivial problems?How can neural...
Book where aliens are selecting humans for food consumption
Indirectly access environment variable
It took me a lot of time to make this, pls like. (YouTube Comments #1)
Which password policy is more secure: one password of length 9 vs. two passwords each of length 8?
Why did other German political parties disband so fast when Hitler was appointed chancellor?
Why don't American passenger airlines operate dedicated cargo flights any more?
Why does lambda auto& parameter choose const overload?
Why do stocks necessarily drop during a recession?
What is the wife of a henpecked husband called?
Draw one function, varying color by (gradient) using another function's value
What to do when being responsible for data protection in your lab, yet advice is ignored?
What is better: yes / no radio, or simple checkbox?
Why zero tolerance on nudity in space?
Why did the villain in the first Men in Black movie care about Earth's Cockroaches?
Caruana vs Carlsen game 10 (WCC) why not 18...Nxb6?
Using only 1s, make 29 with the minimum number of digits
Can you combine War Caster, whip, and Warlock Features to EB enemies with reach?
What makes the Forgotten Realms "forgotten"?
Do authors have to be politically correct in article-writing?
Slow moving projectiles from a hand-held weapon - how do they reach the target?
How to explain planetary rings pulsating?
Parsing a string of key-value pairs as a dictionary
Eww, those bytes are gross
Would a National Army of mercenaries be a feasible idea?
Are there neural networks with very few nodes that decently solve non-trivial problems?
How can neural networks deal with varying input sizes?What sort of game problems can Neural-Networks and Genetic Algorithms solve, and how are they typically implemented?Neural networks efficiently solve traveling salesmen problems?Solving Crossword PuzzlesFramework for Joining Multiple Modular Artificial Neural NetworksNon-linear regression. Universal function approximation with deep neural networksWhat are neural networks?Would this work to prevent forgetting: train a neural net with N nodes. Then, add more nodes and stop training the original nodesAre Modular Neural Networks more effective than large, monolithic networks at any tasks?Why neural networks are not used for the implementation of autonomous (e.g. BDI) agents?
$begingroup$
I'm interested in knowing whether there exist any neural network, that solves (with >=80% accuracy) any nontrivial problem, that uses very few nodes (where 20 nodes is not a hard limit). I want to develop an intuition on sizes of neural networks.
neural-networks
New contributor
$endgroup$
add a comment |
$begingroup$
I'm interested in knowing whether there exist any neural network, that solves (with >=80% accuracy) any nontrivial problem, that uses very few nodes (where 20 nodes is not a hard limit). I want to develop an intuition on sizes of neural networks.
neural-networks
New contributor
$endgroup$
$begingroup$
Universal approximation theorem: a neural network with one hidden layer can approximate any "reasonable" function given a sufficient number of nodes in the hidden layer.
$endgroup$
– nbro
2 hours ago
1
$begingroup$
I think it will not be easy to answer your question. What do you mean by "non-trivial problem"?
$endgroup$
– nbro
2 hours ago
add a comment |
$begingroup$
I'm interested in knowing whether there exist any neural network, that solves (with >=80% accuracy) any nontrivial problem, that uses very few nodes (where 20 nodes is not a hard limit). I want to develop an intuition on sizes of neural networks.
neural-networks
New contributor
$endgroup$
I'm interested in knowing whether there exist any neural network, that solves (with >=80% accuracy) any nontrivial problem, that uses very few nodes (where 20 nodes is not a hard limit). I want to develop an intuition on sizes of neural networks.
neural-networks
neural-networks
New contributor
New contributor
edited 1 hour ago
nbro
1,418621
1,418621
New contributor
asked 3 hours ago
Guillermo MosseGuillermo Mosse
1163
1163
New contributor
New contributor
$begingroup$
Universal approximation theorem: a neural network with one hidden layer can approximate any "reasonable" function given a sufficient number of nodes in the hidden layer.
$endgroup$
– nbro
2 hours ago
1
$begingroup$
I think it will not be easy to answer your question. What do you mean by "non-trivial problem"?
$endgroup$
– nbro
2 hours ago
add a comment |
$begingroup$
Universal approximation theorem: a neural network with one hidden layer can approximate any "reasonable" function given a sufficient number of nodes in the hidden layer.
$endgroup$
– nbro
2 hours ago
1
$begingroup$
I think it will not be easy to answer your question. What do you mean by "non-trivial problem"?
$endgroup$
– nbro
2 hours ago
$begingroup$
Universal approximation theorem: a neural network with one hidden layer can approximate any "reasonable" function given a sufficient number of nodes in the hidden layer.
$endgroup$
– nbro
2 hours ago
$begingroup$
Universal approximation theorem: a neural network with one hidden layer can approximate any "reasonable" function given a sufficient number of nodes in the hidden layer.
$endgroup$
– nbro
2 hours ago
1
1
$begingroup$
I think it will not be easy to answer your question. What do you mean by "non-trivial problem"?
$endgroup$
– nbro
2 hours ago
$begingroup$
I think it will not be easy to answer your question. What do you mean by "non-trivial problem"?
$endgroup$
– nbro
2 hours ago
add a comment |
1 Answer
1
active
oldest
votes
$begingroup$
Even if it’s impossible to answer this question properly, as non trivial is not well defined (maybe the author will edit this questions later, to specify it better), I take the opportunity to point this paper which looks interesting to me
Smallest Neural Network to Learn the Ising Criticality
Assuming you have a general idea of the Ising Model I think the problem of identifying the critical temperature from a data driver perspective can be considered as non trivial and the paper shows how the authors have improved the performance related to solve this task with NN passing from 100 Hidden Neurons, as performed in this paper Machine learning phases of matter from 2017, to only 2 Hidden Neurons
Just my cents:
- reducing the neurons, while keeping good performance, should help in terms of neural processing interpretability which is notoriously obscure and its complexity grows (exponentially) with the number of neurons
$endgroup$
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: "658"
};
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
},
noCode: true, onDemand: true,
discardSelector: ".discard-answer"
,immediatelyShowMarkdownHelp:true
});
}
});
Guillermo Mosse 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%2fai.stackexchange.com%2fquestions%2f10944%2fare-there-neural-networks-with-very-few-nodes-that-decently-solve-non-trivial-pr%23new-answer', 'question_page');
}
);
Post as a guest
Required, but never shown
1 Answer
1
active
oldest
votes
1 Answer
1
active
oldest
votes
active
oldest
votes
active
oldest
votes
$begingroup$
Even if it’s impossible to answer this question properly, as non trivial is not well defined (maybe the author will edit this questions later, to specify it better), I take the opportunity to point this paper which looks interesting to me
Smallest Neural Network to Learn the Ising Criticality
Assuming you have a general idea of the Ising Model I think the problem of identifying the critical temperature from a data driver perspective can be considered as non trivial and the paper shows how the authors have improved the performance related to solve this task with NN passing from 100 Hidden Neurons, as performed in this paper Machine learning phases of matter from 2017, to only 2 Hidden Neurons
Just my cents:
- reducing the neurons, while keeping good performance, should help in terms of neural processing interpretability which is notoriously obscure and its complexity grows (exponentially) with the number of neurons
$endgroup$
add a comment |
$begingroup$
Even if it’s impossible to answer this question properly, as non trivial is not well defined (maybe the author will edit this questions later, to specify it better), I take the opportunity to point this paper which looks interesting to me
Smallest Neural Network to Learn the Ising Criticality
Assuming you have a general idea of the Ising Model I think the problem of identifying the critical temperature from a data driver perspective can be considered as non trivial and the paper shows how the authors have improved the performance related to solve this task with NN passing from 100 Hidden Neurons, as performed in this paper Machine learning phases of matter from 2017, to only 2 Hidden Neurons
Just my cents:
- reducing the neurons, while keeping good performance, should help in terms of neural processing interpretability which is notoriously obscure and its complexity grows (exponentially) with the number of neurons
$endgroup$
add a comment |
$begingroup$
Even if it’s impossible to answer this question properly, as non trivial is not well defined (maybe the author will edit this questions later, to specify it better), I take the opportunity to point this paper which looks interesting to me
Smallest Neural Network to Learn the Ising Criticality
Assuming you have a general idea of the Ising Model I think the problem of identifying the critical temperature from a data driver perspective can be considered as non trivial and the paper shows how the authors have improved the performance related to solve this task with NN passing from 100 Hidden Neurons, as performed in this paper Machine learning phases of matter from 2017, to only 2 Hidden Neurons
Just my cents:
- reducing the neurons, while keeping good performance, should help in terms of neural processing interpretability which is notoriously obscure and its complexity grows (exponentially) with the number of neurons
$endgroup$
Even if it’s impossible to answer this question properly, as non trivial is not well defined (maybe the author will edit this questions later, to specify it better), I take the opportunity to point this paper which looks interesting to me
Smallest Neural Network to Learn the Ising Criticality
Assuming you have a general idea of the Ising Model I think the problem of identifying the critical temperature from a data driver perspective can be considered as non trivial and the paper shows how the authors have improved the performance related to solve this task with NN passing from 100 Hidden Neurons, as performed in this paper Machine learning phases of matter from 2017, to only 2 Hidden Neurons
Just my cents:
- reducing the neurons, while keeping good performance, should help in terms of neural processing interpretability which is notoriously obscure and its complexity grows (exponentially) with the number of neurons
answered 1 hour ago
Nicola BerniniNicola Bernini
511
511
add a comment |
add a comment |
Guillermo Mosse is a new contributor. Be nice, and check out our Code of Conduct.
Guillermo Mosse is a new contributor. Be nice, and check out our Code of Conduct.
Guillermo Mosse is a new contributor. Be nice, and check out our Code of Conduct.
Guillermo Mosse is a new contributor. Be nice, and check out our Code of Conduct.
Thanks for contributing an answer to Artificial Intelligence 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%2fai.stackexchange.com%2fquestions%2f10944%2fare-there-neural-networks-with-very-few-nodes-that-decently-solve-non-trivial-pr%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
$begingroup$
Universal approximation theorem: a neural network with one hidden layer can approximate any "reasonable" function given a sufficient number of nodes in the hidden layer.
$endgroup$
– nbro
2 hours ago
1
$begingroup$
I think it will not be easy to answer your question. What do you mean by "non-trivial problem"?
$endgroup$
– nbro
2 hours ago