How does the number of hidden neurons affect the output? Announcing the arrival of Valued Associate #679: Cesar Manara Planned maintenance scheduled April 23, 2019 at 23:30 UTC (7:30pm US/Eastern) 2019 Moderator Election Q&A - Questionnaire 2019 Community Moderator Election ResultsHow to fight underfitting in a deep neural netNeural Network Hidden Neuron Selection StrategyImportance of Random initialisation VS number of hidden unitsWhy does my Multilayer Perceptron only classify linearly?Cost/loss functions for multi-tasking regression neural networksCan a single-layer ANN get XOR wrong?Ensemble models - neural network input both original data and predictions of other models?Is a Neural Network with 20 times the number of input neurons (on hidden layers) guaranteed to overfit? When is this not so?Calculating sin function with neural network using pythonWhat does the “Loss” value given by Keras mean?
Should a wizard buy fine inks every time he want to copy spells into his spellbook?
Why weren't discrete x86 CPUs ever used in game hardware?
Is multiple magic items in one inherently imbalanced?
What is the origin of 落第?
After Sam didn't return home in the end, were he and Al still friends?
Universal covering space of the real projective line?
Sally's older brother
My mentor says to set image to Fine instead of RAW — how is this different from JPG?
How can a team of shapeshifters communicate?
As a dual citizen, my US passport will expire one day after traveling to the US. Will this work?
Relating to the President and obstruction, were Mueller's conclusions preordained?
Differences to CCompactSize and CVarInt
Printing attributes of selection in ArcPy?
Positioning dot before text in math mode
How to write capital alpha?
I can't produce songs
Why complex landing gears are used instead of simple,reliability and light weight muscle wire or shape memory alloys?
What are the main differences between Stargate SG-1 cuts?
Does silver oxide react with hydrogen sulfide?
Is CEO the "profession" with the most psychopaths?
Tips to organize LaTeX presentations for a semester
Why not send Voyager 3 and 4 following up the paths taken by Voyager 1 and 2 to re-transmit signals of later as they fly away from Earth?
How can I prevent/balance waiting and turtling as a response to cooldown mechanics
What is the difference between a "ranged attack" and a "ranged weapon attack"?
How does the number of hidden neurons affect the output?
Announcing the arrival of Valued Associate #679: Cesar Manara
Planned maintenance scheduled April 23, 2019 at 23:30 UTC (7:30pm US/Eastern)
2019 Moderator Election Q&A - Questionnaire
2019 Community Moderator Election ResultsHow to fight underfitting in a deep neural netNeural Network Hidden Neuron Selection StrategyImportance of Random initialisation VS number of hidden unitsWhy does my Multilayer Perceptron only classify linearly?Cost/loss functions for multi-tasking regression neural networksCan a single-layer ANN get XOR wrong?Ensemble models - neural network input both original data and predictions of other models?Is a Neural Network with 20 times the number of input neurons (on hidden layers) guaranteed to overfit? When is this not so?Calculating sin function with neural network using pythonWhat does the “Loss” value given by Keras mean?
$begingroup$
I'm currently creating neural networks within MatLab, and I was wondering how does the number of hidden neurons affect the output? There is 1 hidden layer only on both. I did two tests on the same data, one with 5 neurons, and one with 10 neurons. The test with 5 neurons had a smaller Mean Square Error, however, the MSE was the smallest at epoch 4, whereas, in the one with 10 neurons, the Mean Square Error was larger, however, the MSE was smallest at epoch 3.
I was wondering of an explanation for this, and I thought that since there is more neurons in the test with 10 neurons, it is able to process/learn data faster, which explains the smaller epoch, however, the larger amount of neurons means that data isn't processed in as much detail as it would be with 5 neurons, which increases the Mean Square Error, and it would be the opposite of this for the 5 neurons.
Can anyone tell me if i'm on the right track at all with that explanation? I'm completely new to AI in general, so excuse me if I got anything completely wrong.
neural-network
asked Apr 4 at 10:28
Kappa123Kappa123
62
$endgroup$
add a comment |
$begingroup$
I'm currently creating neural networks within MatLab, and I was wondering how does the number of hidden neurons affect the output? There is 1 hidden layer only on both. I did two tests on the same data, one with 5 neurons, and one with 10 neurons. The test with 5 neurons had a smaller Mean Square Error, however, the MSE was the smallest at epoch 4, whereas, in the one with 10 neurons, the Mean Square Error was larger, however, the MSE was smallest at epoch 3.
I was wondering of an explanation for this, and I thought that since there is more neurons in the test with 10 neurons, it is able to process/learn data faster, which explains the smaller epoch, however, the larger amount of neurons means that data isn't processed in as much detail as it would be with 5 neurons, which increases the Mean Square Error, and it would be the opposite of this for the 5 neurons.
Can anyone tell me if i'm on the right track at all with that explanation? I'm completely new to AI in general, so excuse me if I got anything completely wrong.
neural-network
asked Apr 4 at 10:28
Kappa123Kappa123
62
$endgroup$
1
$begingroup$
Did MSE on Validation set show similar results ?
$endgroup$
– Shamit Verma
Apr 4 at 10:44
$begingroup$
can you please give exact numbers of MSEs?
$endgroup$
– Preet
Apr 4 at 12:16
$begingroup$
@Preet sure, 5 neurons: 0.13201, smallest MSE at epoch 4, 10 neurons: 0.14386, smallest MSE at epoch 3
$endgroup$
– Kappa123
Apr 4 at 22:35
add a comment |
$begingroup$
I'm currently creating neural networks within MatLab, and I was wondering how does the number of hidden neurons affect the output? There is 1 hidden layer only on both. I did two tests on the same data, one with 5 neurons, and one with 10 neurons. The test with 5 neurons had a smaller Mean Square Error, however, the MSE was the smallest at epoch 4, whereas, in the one with 10 neurons, the Mean Square Error was larger, however, the MSE was smallest at epoch 3.
I was wondering of an explanation for this, and I thought that since there is more neurons in the test with 10 neurons, it is able to process/learn data faster, which explains the smaller epoch, however, the larger amount of neurons means that data isn't processed in as much detail as it would be with 5 neurons, which increases the Mean Square Error, and it would be the opposite of this for the 5 neurons.
Can anyone tell me if i'm on the right track at all with that explanation? I'm completely new to AI in general, so excuse me if I got anything completely wrong.
neural-network
asked Apr 4 at 10:28
Kappa123Kappa123
62
$endgroup$
I'm currently creating neural networks within MatLab, and I was wondering how does the number of hidden neurons affect the output? There is 1 hidden layer only on both. I did two tests on the same data, one with 5 neurons, and one with 10 neurons. The test with 5 neurons had a smaller Mean Square Error, however, the MSE was the smallest at epoch 4, whereas, in the one with 10 neurons, the Mean Square Error was larger, however, the MSE was smallest at epoch 3.
I was wondering of an explanation for this, and I thought that since there is more neurons in the test with 10 neurons, it is able to process/learn data faster, which explains the smaller epoch, however, the larger amount of neurons means that data isn't processed in as much detail as it would be with 5 neurons, which increases the Mean Square Error, and it would be the opposite of this for the 5 neurons.
Can anyone tell me if i'm on the right track at all with that explanation? I'm completely new to AI in general, so excuse me if I got anything completely wrong.
neural-network
neural-network
asked Apr 4 at 10:28
Kappa123Kappa123
62
asked Apr 4 at 10:28
Kappa123Kappa123
62
asked Apr 4 at 10:28
Kappa123Kappa123
62
asked Apr 4 at 10:28
Kappa123Kappa123
62
asked Apr 4 at 10:28
Kappa123Kappa123
62
62
1
$begingroup$
Did MSE on Validation set show similar results ?
$endgroup$
– Shamit Verma
Apr 4 at 10:44
$begingroup$
can you please give exact numbers of MSEs?
$endgroup$
– Preet
Apr 4 at 12:16
$begingroup$
@Preet sure, 5 neurons: 0.13201, smallest MSE at epoch 4, 10 neurons: 0.14386, smallest MSE at epoch 3
$endgroup$
– Kappa123
Apr 4 at 22:35
add a comment |
1
$begingroup$
Did MSE on Validation set show similar results ?
$endgroup$
– Shamit Verma
Apr 4 at 10:44
$begingroup$
can you please give exact numbers of MSEs?
$endgroup$
– Preet
Apr 4 at 12:16
$begingroup$
@Preet sure, 5 neurons: 0.13201, smallest MSE at epoch 4, 10 neurons: 0.14386, smallest MSE at epoch 3
$endgroup$
– Kappa123
Apr 4 at 22:35
1
1
$begingroup$
Did MSE on Validation set show similar results ?
$endgroup$
– Shamit Verma
Apr 4 at 10:44
$begingroup$
Did MSE on Validation set show similar results ?
$endgroup$
– Shamit Verma
Apr 4 at 10:44
$begingroup$
can you please give exact numbers of MSEs?
$endgroup$
– Preet
Apr 4 at 12:16
$begingroup$
can you please give exact numbers of MSEs?
$endgroup$
– Preet
Apr 4 at 12:16
$begingroup$
@Preet sure, 5 neurons: 0.13201, smallest MSE at epoch 4, 10 neurons: 0.14386, smallest MSE at epoch 3
$endgroup$
– Kappa123
Apr 4 at 22:35
$begingroup$
@Preet sure, 5 neurons: 0.13201, smallest MSE at epoch 4, 10 neurons: 0.14386, smallest MSE at epoch 3
$endgroup$
– Kappa123
Apr 4 at 22:35
add a comment |
0
active
oldest
votes
Your Answer
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
);
);
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%2f48603%2fhow-does-the-number-of-hidden-neurons-affect-the-output%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
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%2f48603%2fhow-does-the-number-of-hidden-neurons-affect-the-output%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
1
$begingroup$
Did MSE on Validation set show similar results ?
$endgroup$
– Shamit Verma
Apr 4 at 10:44
$begingroup$
can you please give exact numbers of MSEs?
$endgroup$
– Preet
Apr 4 at 12:16
$begingroup$
@Preet sure, 5 neurons: 0.13201, smallest MSE at epoch 4, 10 neurons: 0.14386, smallest MSE at epoch 3
$endgroup$
– Kappa123
Apr 4 at 22:35