Why do neural networks need so many examples to perform?Examples of drastic improvements when using deep...
How can I deduce the power of a capacitor from its datasheet?
Is the percentage symbol a constant?
Lubuntu 18.10 File Manager: How to view directory tree structure?
Given a total recursive function, can you always compute its fixed-point?
Why "rm -r" is unable to delete this folder?
Is there any danger of my neighbor having my wife's signature?
Modern Algebraic Geometry and Analytic Number Theory
What's the reason that we have a different number of days each month?
What can I do to encourage my players to use their consumables?
Are all power cords made equal?
Would water spill from a bowl in a Bag of Holding?
How do I fight with Heavy Armor as a Wizard with Tenser's Transformation?
How do I add a strong "onion flavor" to the biryani (in restaurant style)?
How to draw a node with two options using TikZ graphs in LaTeX
Where does documentation like business and software requirement spec docs fit in an agile project?
Even as admin, I cannot edit DefaultFonts.plist for Notes.app. What am I doing wrong?
Was Opportunity's last message to Earth "My battery is low and it's getting dark"?
What is an explicit bijection in combinatorics?
Why did Ylvis use "go" instead of "say" in phrases like "Dog goes 'woof'"?
In the Lost in Space intro why was Dr. Smith actor listed as a special guest star?
How to know if I am a 'Real Developer'
Is it possible to detect 100% of SQLi with a simple regex?
Do the speed limit reductions due to pollution also apply to electric cars in France?
Isn't a semicolon (';') needed after a function declaration in C++?
Why do neural networks need so many examples to perform?
Examples of drastic improvements when using deep neural networksDoes Neural Networks based classification need a dimension reduction?Do Neural Networks need “compound” features?Overtraining Neural Networks?Why use gradient descent with neural networks?To what extent are convolutional neural networks inspired by biology?Deep networks vs shallow networks: why do we need depth?One big neural network or many small neural networks?Why do neural networks need feature selection / engineering?Deep neural networks versus tall neural networks
$begingroup$
So we are talking artificial intelligence.
I think human child at 2 needs like 5 instances of a car to be able to identify it with reasonable accuracy regardless of color, make, etc. When my son was 2, he was able to identify trams and trains, even though he had seen just few. He was usually confusing one with each other, apparently his NN was not trained enough, but still.
To paraphrase myself, I could ask what ANN’s miss to be able to learn way quicker? Is transfer learning an answer?
neural-networks neuroscience
asked 5 hours ago
MarcinMarcin
1767
$endgroup$
add a comment |
$begingroup$
So we are talking artificial intelligence.
I think human child at 2 needs like 5 instances of a car to be able to identify it with reasonable accuracy regardless of color, make, etc. When my son was 2, he was able to identify trams and trains, even though he had seen just few. He was usually confusing one with each other, apparently his NN was not trained enough, but still.
To paraphrase myself, I could ask what ANN’s miss to be able to learn way quicker? Is transfer learning an answer?
neural-networks neuroscience
asked 5 hours ago
MarcinMarcin
1767
$endgroup$
$begingroup$
Elephants might be a better example than cars. As others have noted, a child may have seen many cars before hearing the label, so if their mind already defines "natural kinds" it now has a label for one. However, a Western child indisputably develops a good elephant-classifying system on the basis of just a few data.
$endgroup$
– J.G.
11 mins ago
add a comment |
$begingroup$
So we are talking artificial intelligence.
I think human child at 2 needs like 5 instances of a car to be able to identify it with reasonable accuracy regardless of color, make, etc. When my son was 2, he was able to identify trams and trains, even though he had seen just few. He was usually confusing one with each other, apparently his NN was not trained enough, but still.
To paraphrase myself, I could ask what ANN’s miss to be able to learn way quicker? Is transfer learning an answer?
neural-networks neuroscience
asked 5 hours ago
MarcinMarcin
1767
$endgroup$
So we are talking artificial intelligence.
I think human child at 2 needs like 5 instances of a car to be able to identify it with reasonable accuracy regardless of color, make, etc. When my son was 2, he was able to identify trams and trains, even though he had seen just few. He was usually confusing one with each other, apparently his NN was not trained enough, but still.
To paraphrase myself, I could ask what ANN’s miss to be able to learn way quicker? Is transfer learning an answer?
neural-networks neuroscience
neural-networks neuroscience
asked 5 hours ago
MarcinMarcin
1767
asked 5 hours ago
MarcinMarcin
1767
asked 5 hours ago
MarcinMarcin
1767
asked 5 hours ago
MarcinMarcin
1767
asked 5 hours ago
MarcinMarcin
1767
1767
$begingroup$
Elephants might be a better example than cars. As others have noted, a child may have seen many cars before hearing the label, so if their mind already defines "natural kinds" it now has a label for one. However, a Western child indisputably develops a good elephant-classifying system on the basis of just a few data.
$endgroup$
– J.G.
11 mins ago
add a comment |
$begingroup$
Elephants might be a better example than cars. As others have noted, a child may have seen many cars before hearing the label, so if their mind already defines "natural kinds" it now has a label for one. However, a Western child indisputably develops a good elephant-classifying system on the basis of just a few data.
$endgroup$
– J.G.
11 mins ago
$begingroup$
Elephants might be a better example than cars. As others have noted, a child may have seen many cars before hearing the label, so if their mind already defines "natural kinds" it now has a label for one. However, a Western child indisputably develops a good elephant-classifying system on the basis of just a few data.
$endgroup$
– J.G.
11 mins ago
$begingroup$
Elephants might be a better example than cars. As others have noted, a child may have seen many cars before hearing the label, so if their mind already defines "natural kinds" it now has a label for one. However, a Western child indisputably develops a good elephant-classifying system on the basis of just a few data.
$endgroup$
– J.G.
11 mins ago
add a comment |
3 Answers
3
active
oldest
votes
$begingroup$
First of all, at age two, child knows a lot about world and actively applies this knowledge. Child does a lot of "transfer learning" by applying this knowledge to new concepts.
Second, before seeing those five "labeled" examples of car, child sees a lot of cars on the street, on TV, toy cars etc., so also a lot of "unsupervised learning" happens beforehand.
Finally, neural networks have almost nothing in common with human brain, so there's not much point in comparing them. Also notice that there are algorithms for one shot learning, and pretty much research on it currently happens.
answered 4 hours ago
Tim♦Tim
58k9127219
$endgroup$
add a comment |
$begingroup$
There's a kind of goalpost moving that underlies this question. It used to be that NNs weren't very good at image recognition, so no one compared them to humans. Now that NNs are good at image tasks, suddenly it's the fault of NNs that they require a lot of training data to be comparable to children.
You can also turn this logic on its head. Suppose a child sees a number of cars the day that it's born. I wouldn't expect the child to be able to pick out a car the next day, or the next week even though it's seen so many examples. Why are newborns so slow to learn? Because it takes a lot of exposure to the real world and time to change the child's neural pathways ("training data").
answered 3 hours ago
SycoraxSycorax
40.4k12103203
$endgroup$
add a comment |
$begingroup$
Please remember that neural networks are very complex structures with lots of parametres to tune, therefore you should not expect it to "learn" without huge numbers of examples.
This is the reason why simpler models are often preferred when samples are not huge.
answered 2 hours ago
asdfasdf
513
New contributor
asdf is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.
$endgroup$
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: "65"
};
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%2fstats.stackexchange.com%2fquestions%2f394118%2fwhy-do-neural-networks-need-so-many-examples-to-perform%23new-answer', 'question_page');
}
);
Post as a guest
Required, but never shown
3 Answers
3
active
oldest
votes
3 Answers
3
active
oldest
votes
active
oldest
votes
active
oldest
votes
$begingroup$
First of all, at age two, child knows a lot about world and actively applies this knowledge. Child does a lot of "transfer learning" by applying this knowledge to new concepts.
Second, before seeing those five "labeled" examples of car, child sees a lot of cars on the street, on TV, toy cars etc., so also a lot of "unsupervised learning" happens beforehand.
Finally, neural networks have almost nothing in common with human brain, so there's not much point in comparing them. Also notice that there are algorithms for one shot learning, and pretty much research on it currently happens.
answered 4 hours ago
Tim♦Tim
58k9127219
$endgroup$
add a comment |
$begingroup$
First of all, at age two, child knows a lot about world and actively applies this knowledge. Child does a lot of "transfer learning" by applying this knowledge to new concepts.
Second, before seeing those five "labeled" examples of car, child sees a lot of cars on the street, on TV, toy cars etc., so also a lot of "unsupervised learning" happens beforehand.
Finally, neural networks have almost nothing in common with human brain, so there's not much point in comparing them. Also notice that there are algorithms for one shot learning, and pretty much research on it currently happens.
answered 4 hours ago
Tim♦Tim
58k9127219
$endgroup$
add a comment |
$begingroup$
First of all, at age two, child knows a lot about world and actively applies this knowledge. Child does a lot of "transfer learning" by applying this knowledge to new concepts.
Second, before seeing those five "labeled" examples of car, child sees a lot of cars on the street, on TV, toy cars etc., so also a lot of "unsupervised learning" happens beforehand.
Finally, neural networks have almost nothing in common with human brain, so there's not much point in comparing them. Also notice that there are algorithms for one shot learning, and pretty much research on it currently happens.
answered 4 hours ago
Tim♦Tim
58k9127219
$endgroup$
First of all, at age two, child knows a lot about world and actively applies this knowledge. Child does a lot of "transfer learning" by applying this knowledge to new concepts.
Second, before seeing those five "labeled" examples of car, child sees a lot of cars on the street, on TV, toy cars etc., so also a lot of "unsupervised learning" happens beforehand.
Finally, neural networks have almost nothing in common with human brain, so there's not much point in comparing them. Also notice that there are algorithms for one shot learning, and pretty much research on it currently happens.
answered 4 hours ago
Tim♦Tim
58k9127219
answered 4 hours ago
Tim♦Tim
58k9127219
answered 4 hours ago
Tim♦Tim
58k9127219
answered 4 hours ago
Tim♦Tim
58k9127219
58k9127219
add a comment |
add a comment |
$begingroup$
There's a kind of goalpost moving that underlies this question. It used to be that NNs weren't very good at image recognition, so no one compared them to humans. Now that NNs are good at image tasks, suddenly it's the fault of NNs that they require a lot of training data to be comparable to children.
You can also turn this logic on its head. Suppose a child sees a number of cars the day that it's born. I wouldn't expect the child to be able to pick out a car the next day, or the next week even though it's seen so many examples. Why are newborns so slow to learn? Because it takes a lot of exposure to the real world and time to change the child's neural pathways ("training data").
answered 3 hours ago
SycoraxSycorax
40.4k12103203
$endgroup$
add a comment |
$begingroup$
There's a kind of goalpost moving that underlies this question. It used to be that NNs weren't very good at image recognition, so no one compared them to humans. Now that NNs are good at image tasks, suddenly it's the fault of NNs that they require a lot of training data to be comparable to children.
You can also turn this logic on its head. Suppose a child sees a number of cars the day that it's born. I wouldn't expect the child to be able to pick out a car the next day, or the next week even though it's seen so many examples. Why are newborns so slow to learn? Because it takes a lot of exposure to the real world and time to change the child's neural pathways ("training data").
answered 3 hours ago
SycoraxSycorax
40.4k12103203
$endgroup$
add a comment |
$begingroup$
There's a kind of goalpost moving that underlies this question. It used to be that NNs weren't very good at image recognition, so no one compared them to humans. Now that NNs are good at image tasks, suddenly it's the fault of NNs that they require a lot of training data to be comparable to children.
You can also turn this logic on its head. Suppose a child sees a number of cars the day that it's born. I wouldn't expect the child to be able to pick out a car the next day, or the next week even though it's seen so many examples. Why are newborns so slow to learn? Because it takes a lot of exposure to the real world and time to change the child's neural pathways ("training data").
answered 3 hours ago
SycoraxSycorax
40.4k12103203
$endgroup$
There's a kind of goalpost moving that underlies this question. It used to be that NNs weren't very good at image recognition, so no one compared them to humans. Now that NNs are good at image tasks, suddenly it's the fault of NNs that they require a lot of training data to be comparable to children.
You can also turn this logic on its head. Suppose a child sees a number of cars the day that it's born. I wouldn't expect the child to be able to pick out a car the next day, or the next week even though it's seen so many examples. Why are newborns so slow to learn? Because it takes a lot of exposure to the real world and time to change the child's neural pathways ("training data").
answered 3 hours ago
SycoraxSycorax
40.4k12103203
answered 3 hours ago
SycoraxSycorax
40.4k12103203
answered 3 hours ago
SycoraxSycorax
40.4k12103203
answered 3 hours ago
SycoraxSycorax
40.4k12103203
40.4k12103203
add a comment |
add a comment |
$begingroup$
Please remember that neural networks are very complex structures with lots of parametres to tune, therefore you should not expect it to "learn" without huge numbers of examples.
This is the reason why simpler models are often preferred when samples are not huge.
answered 2 hours ago
asdfasdf
513
New contributor
asdf is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.
$endgroup$
add a comment |
$begingroup$
Please remember that neural networks are very complex structures with lots of parametres to tune, therefore you should not expect it to "learn" without huge numbers of examples.
This is the reason why simpler models are often preferred when samples are not huge.
answered 2 hours ago
asdfasdf
513
New contributor
asdf is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.
$endgroup$
add a comment |
$begingroup$
Please remember that neural networks are very complex structures with lots of parametres to tune, therefore you should not expect it to "learn" without huge numbers of examples.
This is the reason why simpler models are often preferred when samples are not huge.
answered 2 hours ago
asdfasdf
513
New contributor
asdf is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.
$endgroup$
Please remember that neural networks are very complex structures with lots of parametres to tune, therefore you should not expect it to "learn" without huge numbers of examples.
This is the reason why simpler models are often preferred when samples are not huge.
answered 2 hours ago
asdfasdf
513
New contributor
asdf is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.
answered 2 hours ago
asdfasdf
513
New contributor
asdf is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.
answered 2 hours ago
asdfasdf
513
answered 2 hours ago
asdfasdf
513
513
New contributor
asdf is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.
New contributor
asdf is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.
asdf is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.
add a comment |
add a comment |
Thanks for contributing an answer to Cross Validated!
- 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%2fstats.stackexchange.com%2fquestions%2f394118%2fwhy-do-neural-networks-need-so-many-examples-to-perform%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
$begingroup$
Elephants might be a better example than cars. As others have noted, a child may have seen many cars before hearing the label, so if their mind already defines "natural kinds" it now has a label for one. However, a Western child indisputably develops a good elephant-classifying system on the basis of just a few data.
$endgroup$
– J.G.
11 mins ago