Few activation functions handling various problems - neural networks
$begingroup$
How can a few activation functions in neural networks handle so many different problems?
I know some basics theory behind ANN, but I can't get what functions like the sigmoid function etc. have in common with for example image classification?
neural-network deep-learning activation-function
edited Aug 8 '18 at 17:31
oW_
3,306933
asked Aug 8 '18 at 15:44
mikinoqwertmikinoqwert
244
$endgroup$
bumped to the homepage by Community♦ 22 hours ago
This question has answers that may be good or bad; the system has marked it active so that they can be reviewed.
add a comment |
$begingroup$
How can a few activation functions in neural networks handle so many different problems?
I know some basics theory behind ANN, but I can't get what functions like the sigmoid function etc. have in common with for example image classification?
neural-network deep-learning activation-function
edited Aug 8 '18 at 17:31
oW_
3,306933
asked Aug 8 '18 at 15:44
mikinoqwertmikinoqwert
244
$endgroup$
bumped to the homepage by Community♦ 22 hours ago
This question has answers that may be good or bad; the system has marked it active so that they can be reviewed.
add a comment |
$begingroup$
How can a few activation functions in neural networks handle so many different problems?
I know some basics theory behind ANN, but I can't get what functions like the sigmoid function etc. have in common with for example image classification?
neural-network deep-learning activation-function
edited Aug 8 '18 at 17:31
oW_
3,306933
asked Aug 8 '18 at 15:44
mikinoqwertmikinoqwert
244
$endgroup$
How can a few activation functions in neural networks handle so many different problems?
I know some basics theory behind ANN, but I can't get what functions like the sigmoid function etc. have in common with for example image classification?
neural-network deep-learning activation-function
neural-network deep-learning activation-function
edited Aug 8 '18 at 17:31
oW_
3,306933
asked Aug 8 '18 at 15:44
mikinoqwertmikinoqwert
244
edited Aug 8 '18 at 17:31
oW_
3,306933
asked Aug 8 '18 at 15:44
mikinoqwertmikinoqwert
244
edited Aug 8 '18 at 17:31
oW_
3,306933
edited Aug 8 '18 at 17:31
oW_
3,306933
edited Aug 8 '18 at 17:31
oW_
3,306933
3,306933
asked Aug 8 '18 at 15:44
mikinoqwertmikinoqwert
244
asked Aug 8 '18 at 15:44
mikinoqwertmikinoqwert
244
asked Aug 8 '18 at 15:44
mikinoqwertmikinoqwert
244
244
bumped to the homepage by Community♦ 22 hours ago
This question has answers that may be good or bad; the system has marked it active so that they can be reviewed.
bumped to the homepage by Community♦ 22 hours ago
This question has answers that may be good or bad; the system has marked it active so that they can be reviewed.
add a comment |
add a comment |
2 Answers
2
active
oldest
votes
$begingroup$
Image classification and other task can be expressed as function approximations and, in theory, neural networks can approximate (almost) any function (given few assumptions on the activation function (see Universal Approx. Theorem)).
However, in practice, not all functions fulfilling these assumptions work equally well. Popular activation functions usually share some properties that allow neural networks to learn efficiently in practice, e.g. they are continuously differentiable (for gradient descent), close to the identity near zero (accelerates initial learning from small random weights) and so on.
Activation functions like the sigmoid function are not directly related to image classification or any other tasks. Rather, they allow for efficient training of neural networks, which, in turn, can represent a wide variety of tasks using different architectures and cost functions.
answered Aug 8 '18 at 17:29
oW_oW_
3,306933
$endgroup$
$begingroup$
But I still don't get what in common have any function connected with some real-life-problems to tanh, sigmoid etc. And why do we use that kind of funcs, but not sin/cos. I know it is stupid question ,but I don't get it.
$endgroup$
– mikinoqwert
Aug 8 '18 at 17:35
$begingroup$
Not sure I understand 100%. Are you asking (a) what tanh, sigmoid, relu etc. have in common or (b) how sigmoid is related to say image classification? (a) they all allow efficient training of neural networks (cos/sin do not), (b) there is no relationship other than (a). Maybe you can rephrase your questions with a more detailed example?
$endgroup$
– oW_
Aug 8 '18 at 17:42
$begingroup$
I meant, why we use (for any task) sigmoid/tanh/etc. instead of cos/sin.
$endgroup$
– mikinoqwert
Aug 8 '18 at 17:46
add a comment |
$begingroup$
To respond to your additional question of why sigmoid or tanh instead of sin or cos, I would say that while all of these functions are bounded in their output, only sigmoid and tanh are one to one functions.
answered Aug 9 '18 at 2:01
RossDeVitoRossDeVito
1015
$endgroup$
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
});
}
});
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%2f36646%2ffew-activation-functions-handling-various-problems-neural-networks%23new-answer', 'question_page');
}
);
Post as a guest
Required, but never shown
2 Answers
2
active
oldest
votes
2 Answers
2
active
oldest
votes
active
oldest
votes
active
oldest
votes
$begingroup$
Image classification and other task can be expressed as function approximations and, in theory, neural networks can approximate (almost) any function (given few assumptions on the activation function (see Universal Approx. Theorem)).
However, in practice, not all functions fulfilling these assumptions work equally well. Popular activation functions usually share some properties that allow neural networks to learn efficiently in practice, e.g. they are continuously differentiable (for gradient descent), close to the identity near zero (accelerates initial learning from small random weights) and so on.
Activation functions like the sigmoid function are not directly related to image classification or any other tasks. Rather, they allow for efficient training of neural networks, which, in turn, can represent a wide variety of tasks using different architectures and cost functions.
answered Aug 8 '18 at 17:29
oW_oW_
3,306933
$endgroup$
$begingroup$
But I still don't get what in common have any function connected with some real-life-problems to tanh, sigmoid etc. And why do we use that kind of funcs, but not sin/cos. I know it is stupid question ,but I don't get it.
$endgroup$
– mikinoqwert
Aug 8 '18 at 17:35
$begingroup$
Not sure I understand 100%. Are you asking (a) what tanh, sigmoid, relu etc. have in common or (b) how sigmoid is related to say image classification? (a) they all allow efficient training of neural networks (cos/sin do not), (b) there is no relationship other than (a). Maybe you can rephrase your questions with a more detailed example?
$endgroup$
– oW_
Aug 8 '18 at 17:42
$begingroup$
I meant, why we use (for any task) sigmoid/tanh/etc. instead of cos/sin.
$endgroup$
– mikinoqwert
Aug 8 '18 at 17:46
add a comment |
$begingroup$
Image classification and other task can be expressed as function approximations and, in theory, neural networks can approximate (almost) any function (given few assumptions on the activation function (see Universal Approx. Theorem)).
However, in practice, not all functions fulfilling these assumptions work equally well. Popular activation functions usually share some properties that allow neural networks to learn efficiently in practice, e.g. they are continuously differentiable (for gradient descent), close to the identity near zero (accelerates initial learning from small random weights) and so on.
Activation functions like the sigmoid function are not directly related to image classification or any other tasks. Rather, they allow for efficient training of neural networks, which, in turn, can represent a wide variety of tasks using different architectures and cost functions.
answered Aug 8 '18 at 17:29
oW_oW_
3,306933
$endgroup$
$begingroup$
But I still don't get what in common have any function connected with some real-life-problems to tanh, sigmoid etc. And why do we use that kind of funcs, but not sin/cos. I know it is stupid question ,but I don't get it.
$endgroup$
– mikinoqwert
Aug 8 '18 at 17:35
$begingroup$
Not sure I understand 100%. Are you asking (a) what tanh, sigmoid, relu etc. have in common or (b) how sigmoid is related to say image classification? (a) they all allow efficient training of neural networks (cos/sin do not), (b) there is no relationship other than (a). Maybe you can rephrase your questions with a more detailed example?
$endgroup$
– oW_
Aug 8 '18 at 17:42
$begingroup$
I meant, why we use (for any task) sigmoid/tanh/etc. instead of cos/sin.
$endgroup$
– mikinoqwert
Aug 8 '18 at 17:46
add a comment |
$begingroup$
Image classification and other task can be expressed as function approximations and, in theory, neural networks can approximate (almost) any function (given few assumptions on the activation function (see Universal Approx. Theorem)).
However, in practice, not all functions fulfilling these assumptions work equally well. Popular activation functions usually share some properties that allow neural networks to learn efficiently in practice, e.g. they are continuously differentiable (for gradient descent), close to the identity near zero (accelerates initial learning from small random weights) and so on.
Activation functions like the sigmoid function are not directly related to image classification or any other tasks. Rather, they allow for efficient training of neural networks, which, in turn, can represent a wide variety of tasks using different architectures and cost functions.
answered Aug 8 '18 at 17:29
oW_oW_
3,306933
$endgroup$
Image classification and other task can be expressed as function approximations and, in theory, neural networks can approximate (almost) any function (given few assumptions on the activation function (see Universal Approx. Theorem)).
However, in practice, not all functions fulfilling these assumptions work equally well. Popular activation functions usually share some properties that allow neural networks to learn efficiently in practice, e.g. they are continuously differentiable (for gradient descent), close to the identity near zero (accelerates initial learning from small random weights) and so on.
Activation functions like the sigmoid function are not directly related to image classification or any other tasks. Rather, they allow for efficient training of neural networks, which, in turn, can represent a wide variety of tasks using different architectures and cost functions.
answered Aug 8 '18 at 17:29
oW_oW_
3,306933
answered Aug 8 '18 at 17:29
oW_oW_
3,306933
answered Aug 8 '18 at 17:29
oW_oW_
3,306933
answered Aug 8 '18 at 17:29
oW_oW_
3,306933
3,306933
$begingroup$
But I still don't get what in common have any function connected with some real-life-problems to tanh, sigmoid etc. And why do we use that kind of funcs, but not sin/cos. I know it is stupid question ,but I don't get it.
$endgroup$
– mikinoqwert
Aug 8 '18 at 17:35
$begingroup$
Not sure I understand 100%. Are you asking (a) what tanh, sigmoid, relu etc. have in common or (b) how sigmoid is related to say image classification? (a) they all allow efficient training of neural networks (cos/sin do not), (b) there is no relationship other than (a). Maybe you can rephrase your questions with a more detailed example?
$endgroup$
– oW_
Aug 8 '18 at 17:42
$begingroup$
I meant, why we use (for any task) sigmoid/tanh/etc. instead of cos/sin.
$endgroup$
– mikinoqwert
Aug 8 '18 at 17:46
add a comment |
$begingroup$
But I still don't get what in common have any function connected with some real-life-problems to tanh, sigmoid etc. And why do we use that kind of funcs, but not sin/cos. I know it is stupid question ,but I don't get it.
$endgroup$
– mikinoqwert
Aug 8 '18 at 17:35
$begingroup$
Not sure I understand 100%. Are you asking (a) what tanh, sigmoid, relu etc. have in common or (b) how sigmoid is related to say image classification? (a) they all allow efficient training of neural networks (cos/sin do not), (b) there is no relationship other than (a). Maybe you can rephrase your questions with a more detailed example?
$endgroup$
– oW_
Aug 8 '18 at 17:42
$begingroup$
I meant, why we use (for any task) sigmoid/tanh/etc. instead of cos/sin.
$endgroup$
– mikinoqwert
Aug 8 '18 at 17:46
$begingroup$
But I still don't get what in common have any function connected with some real-life-problems to tanh, sigmoid etc. And why do we use that kind of funcs, but not sin/cos. I know it is stupid question ,but I don't get it.
$endgroup$
– mikinoqwert
Aug 8 '18 at 17:35
$begingroup$
But I still don't get what in common have any function connected with some real-life-problems to tanh, sigmoid etc. And why do we use that kind of funcs, but not sin/cos. I know it is stupid question ,but I don't get it.
$endgroup$
– mikinoqwert
Aug 8 '18 at 17:35
$begingroup$
Not sure I understand 100%. Are you asking (a) what tanh, sigmoid, relu etc. have in common or (b) how sigmoid is related to say image classification? (a) they all allow efficient training of neural networks (cos/sin do not), (b) there is no relationship other than (a). Maybe you can rephrase your questions with a more detailed example?
$endgroup$
– oW_
Aug 8 '18 at 17:42
$begingroup$
Not sure I understand 100%. Are you asking (a) what tanh, sigmoid, relu etc. have in common or (b) how sigmoid is related to say image classification? (a) they all allow efficient training of neural networks (cos/sin do not), (b) there is no relationship other than (a). Maybe you can rephrase your questions with a more detailed example?
$endgroup$
– oW_
Aug 8 '18 at 17:42
$begingroup$
I meant, why we use (for any task) sigmoid/tanh/etc. instead of cos/sin.
$endgroup$
– mikinoqwert
Aug 8 '18 at 17:46
$begingroup$
I meant, why we use (for any task) sigmoid/tanh/etc. instead of cos/sin.
$endgroup$
– mikinoqwert
Aug 8 '18 at 17:46
add a comment |
$begingroup$
To respond to your additional question of why sigmoid or tanh instead of sin or cos, I would say that while all of these functions are bounded in their output, only sigmoid and tanh are one to one functions.
answered Aug 9 '18 at 2:01
RossDeVitoRossDeVito
1015
$endgroup$
add a comment |
$begingroup$
To respond to your additional question of why sigmoid or tanh instead of sin or cos, I would say that while all of these functions are bounded in their output, only sigmoid and tanh are one to one functions.
answered Aug 9 '18 at 2:01
RossDeVitoRossDeVito
1015
$endgroup$
add a comment |
$begingroup$
To respond to your additional question of why sigmoid or tanh instead of sin or cos, I would say that while all of these functions are bounded in their output, only sigmoid and tanh are one to one functions.
answered Aug 9 '18 at 2:01
RossDeVitoRossDeVito
1015
$endgroup$
To respond to your additional question of why sigmoid or tanh instead of sin or cos, I would say that while all of these functions are bounded in their output, only sigmoid and tanh are one to one functions.
answered Aug 9 '18 at 2:01
RossDeVitoRossDeVito
1015
answered Aug 9 '18 at 2:01
RossDeVitoRossDeVito
1015
answered Aug 9 '18 at 2:01
RossDeVitoRossDeVito
1015
answered Aug 9 '18 at 2:01
RossDeVitoRossDeVito
1015
1015
add a comment |
add a comment |
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%2f36646%2ffew-activation-functions-handling-various-problems-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
