Setting learning rate as negative number for wrong train cases
up vote
0
down vote
favorite
I was watching a video which tells a bit about reinforcement learning, and I learnt that If the robot makes wrong movement then they train the network with negative learning rate. From this method, something has come to my mind.
My question is that "Can I use a data with wrong output to train a neural network?".
To illustrate the method, I ll be using the eye tracker project that I'm working on right now.
In my project There are photos and the points that corresponds the locations that I m looking at that photo. Its like grid (9, 16). If I look at the middle of the screen, it means the output is (4, 7.5). if I look left up side of the screen it means (0,0). Normally for a photo that I'm looking at the middle, we use that photo as input and (4, 7.5) as output to train network using positive learning rate. Now let me rephrase the question. Can I train a model giving a photo that I'm looking at the middle as input and (0,0) as output(label) using negative learning rate?
Thank you, If I made a mistake against the rules of stackoverflow, I'm so sorry. I ll be waiting your valuable answers.
deep-learning reinforcement-learning
asked Nov 19 at 18:27
Faruk Nane
11
|
show 1 more comment
up vote
0
down vote
favorite
I was watching a video which tells a bit about reinforcement learning, and I learnt that If the robot makes wrong movement then they train the network with negative learning rate. From this method, something has come to my mind.
My question is that "Can I use a data with wrong output to train a neural network?".
To illustrate the method, I ll be using the eye tracker project that I'm working on right now.
In my project There are photos and the points that corresponds the locations that I m looking at that photo. Its like grid (9, 16). If I look at the middle of the screen, it means the output is (4, 7.5). if I look left up side of the screen it means (0,0). Normally for a photo that I'm looking at the middle, we use that photo as input and (4, 7.5) as output to train network using positive learning rate. Now let me rephrase the question. Can I train a model giving a photo that I'm looking at the middle as input and (0,0) as output(label) using negative learning rate?
Thank you, If I made a mistake against the rules of stackoverflow, I'm so sorry. I ll be waiting your valuable answers.
deep-learning reinforcement-learning
asked Nov 19 at 18:27
Faruk Nane
11
Yes, you can. But, what would be the reason of passing a wrong ground truth to your training process?
– Neb
Nov 19 at 18:46
If I have no various data to train, I can create more data via this method to increase the certainty when I use squared error loss. But I have doubts about this method. for example lets assume we have a photo named 'X' and its label is (5,5). at first epoch, Let the model gives (2,2) for photo 'X'. if I try to train network with a photo X and label -> (4,4) using negative learning rate, it might send away the point from (2,2) to (1,1) whereas we expect it to send the point (2,2) to (5,5). Did you get what I meant?
– Faruk Nane
Nov 19 at 19:02
You are right. Using a negative learning rate and a wrong ground truth will not necessarly make the learning process converge to the optimal value for your net's parameters
– Neb
Nov 19 at 19:13
So can I say that "when I'm sure that the absolute error for each case is less than 2, I can use this method using points away 2 units." So It'll make the outputs closer to the target point. I don't really know if we can easily say that. because we consider this method as if there are only 2 parameters which is the output point. However a model has many parameters so It might affect so differently. My brain is so confused. I think this might be an academic work, right?
– Faruk Nane
Nov 19 at 19:31
Well, it is difficult to suggests you the path to follow without knowing the exact specifics of your problem. In any case, if you're trying to solve this problem for fun or self-improvement, I'd suggest you to experiment with the solutions you came up with and see if they works.
– Neb
Nov 19 at 19:34
|
show 1 more comment
up vote
0
down vote
favorite
up vote
0
down vote
favorite
I was watching a video which tells a bit about reinforcement learning, and I learnt that If the robot makes wrong movement then they train the network with negative learning rate. From this method, something has come to my mind.
My question is that "Can I use a data with wrong output to train a neural network?".
To illustrate the method, I ll be using the eye tracker project that I'm working on right now.
In my project There are photos and the points that corresponds the locations that I m looking at that photo. Its like grid (9, 16). If I look at the middle of the screen, it means the output is (4, 7.5). if I look left up side of the screen it means (0,0). Normally for a photo that I'm looking at the middle, we use that photo as input and (4, 7.5) as output to train network using positive learning rate. Now let me rephrase the question. Can I train a model giving a photo that I'm looking at the middle as input and (0,0) as output(label) using negative learning rate?
Thank you, If I made a mistake against the rules of stackoverflow, I'm so sorry. I ll be waiting your valuable answers.
deep-learning reinforcement-learning
asked Nov 19 at 18:27
Faruk Nane
11
I was watching a video which tells a bit about reinforcement learning, and I learnt that If the robot makes wrong movement then they train the network with negative learning rate. From this method, something has come to my mind.
My question is that "Can I use a data with wrong output to train a neural network?".
To illustrate the method, I ll be using the eye tracker project that I'm working on right now.
In my project There are photos and the points that corresponds the locations that I m looking at that photo. Its like grid (9, 16). If I look at the middle of the screen, it means the output is (4, 7.5). if I look left up side of the screen it means (0,0). Normally for a photo that I'm looking at the middle, we use that photo as input and (4, 7.5) as output to train network using positive learning rate. Now let me rephrase the question. Can I train a model giving a photo that I'm looking at the middle as input and (0,0) as output(label) using negative learning rate?
Thank you, If I made a mistake against the rules of stackoverflow, I'm so sorry. I ll be waiting your valuable answers.
deep-learning reinforcement-learning
deep-learning reinforcement-learning
asked Nov 19 at 18:27
Faruk Nane
11
asked Nov 19 at 18:27
Faruk Nane
11
edited Nov 23 at 10:27
asked Nov 19 at 18:27
Faruk Nane
11
asked Nov 19 at 18:27
Faruk Nane
11
asked Nov 19 at 18:27
Faruk Nane
11
11
Yes, you can. But, what would be the reason of passing a wrong ground truth to your training process?
– Neb
Nov 19 at 18:46
If I have no various data to train, I can create more data via this method to increase the certainty when I use squared error loss. But I have doubts about this method. for example lets assume we have a photo named 'X' and its label is (5,5). at first epoch, Let the model gives (2,2) for photo 'X'. if I try to train network with a photo X and label -> (4,4) using negative learning rate, it might send away the point from (2,2) to (1,1) whereas we expect it to send the point (2,2) to (5,5). Did you get what I meant?
– Faruk Nane
Nov 19 at 19:02
You are right. Using a negative learning rate and a wrong ground truth will not necessarly make the learning process converge to the optimal value for your net's parameters
– Neb
Nov 19 at 19:13
So can I say that "when I'm sure that the absolute error for each case is less than 2, I can use this method using points away 2 units." So It'll make the outputs closer to the target point. I don't really know if we can easily say that. because we consider this method as if there are only 2 parameters which is the output point. However a model has many parameters so It might affect so differently. My brain is so confused. I think this might be an academic work, right?
– Faruk Nane
Nov 19 at 19:31
Well, it is difficult to suggests you the path to follow without knowing the exact specifics of your problem. In any case, if you're trying to solve this problem for fun or self-improvement, I'd suggest you to experiment with the solutions you came up with and see if they works.
– Neb
Nov 19 at 19:34
|
show 1 more comment
Yes, you can. But, what would be the reason of passing a wrong ground truth to your training process?
– Neb
Nov 19 at 18:46
If I have no various data to train, I can create more data via this method to increase the certainty when I use squared error loss. But I have doubts about this method. for example lets assume we have a photo named 'X' and its label is (5,5). at first epoch, Let the model gives (2,2) for photo 'X'. if I try to train network with a photo X and label -> (4,4) using negative learning rate, it might send away the point from (2,2) to (1,1) whereas we expect it to send the point (2,2) to (5,5). Did you get what I meant?
– Faruk Nane
Nov 19 at 19:02
You are right. Using a negative learning rate and a wrong ground truth will not necessarly make the learning process converge to the optimal value for your net's parameters
– Neb
Nov 19 at 19:13
So can I say that "when I'm sure that the absolute error for each case is less than 2, I can use this method using points away 2 units." So It'll make the outputs closer to the target point. I don't really know if we can easily say that. because we consider this method as if there are only 2 parameters which is the output point. However a model has many parameters so It might affect so differently. My brain is so confused. I think this might be an academic work, right?
– Faruk Nane
Nov 19 at 19:31
Well, it is difficult to suggests you the path to follow without knowing the exact specifics of your problem. In any case, if you're trying to solve this problem for fun or self-improvement, I'd suggest you to experiment with the solutions you came up with and see if they works.
– Neb
Nov 19 at 19:34
Yes, you can. But, what would be the reason of passing a wrong ground truth to your training process?
– Neb
Nov 19 at 18:46
Yes, you can. But, what would be the reason of passing a wrong ground truth to your training process?
– Neb
Nov 19 at 18:46
If I have no various data to train, I can create more data via this method to increase the certainty when I use squared error loss. But I have doubts about this method. for example lets assume we have a photo named 'X' and its label is (5,5). at first epoch, Let the model gives (2,2) for photo 'X'. if I try to train network with a photo X and label -> (4,4) using negative learning rate, it might send away the point from (2,2) to (1,1) whereas we expect it to send the point (2,2) to (5,5). Did you get what I meant?
– Faruk Nane
Nov 19 at 19:02
If I have no various data to train, I can create more data via this method to increase the certainty when I use squared error loss. But I have doubts about this method. for example lets assume we have a photo named 'X' and its label is (5,5). at first epoch, Let the model gives (2,2) for photo 'X'. if I try to train network with a photo X and label -> (4,4) using negative learning rate, it might send away the point from (2,2) to (1,1) whereas we expect it to send the point (2,2) to (5,5). Did you get what I meant?
– Faruk Nane
Nov 19 at 19:02
You are right. Using a negative learning rate and a wrong ground truth will not necessarly make the learning process converge to the optimal value for your net's parameters
– Neb
Nov 19 at 19:13
You are right. Using a negative learning rate and a wrong ground truth will not necessarly make the learning process converge to the optimal value for your net's parameters
– Neb
Nov 19 at 19:13
So can I say that "when I'm sure that the absolute error for each case is less than 2, I can use this method using points away 2 units." So It'll make the outputs closer to the target point. I don't really know if we can easily say that. because we consider this method as if there are only 2 parameters which is the output point. However a model has many parameters so It might affect so differently. My brain is so confused. I think this might be an academic work, right?
– Faruk Nane
Nov 19 at 19:31
So can I say that "when I'm sure that the absolute error for each case is less than 2, I can use this method using points away 2 units." So It'll make the outputs closer to the target point. I don't really know if we can easily say that. because we consider this method as if there are only 2 parameters which is the output point. However a model has many parameters so It might affect so differently. My brain is so confused. I think this might be an academic work, right?
– Faruk Nane
Nov 19 at 19:31
Well, it is difficult to suggests you the path to follow without knowing the exact specifics of your problem. In any case, if you're trying to solve this problem for fun or self-improvement, I'd suggest you to experiment with the solutions you came up with and see if they works.
– Neb
Nov 19 at 19:34
Well, it is difficult to suggests you the path to follow without knowing the exact specifics of your problem. In any case, if you're trying to solve this problem for fun or self-improvement, I'd suggest you to experiment with the solutions you came up with and see if they works.
– Neb
Nov 19 at 19:34
|
show 1 more comment
active
oldest
votes
Your Answer
StackExchange.ifUsing("editor", function () {
StackExchange.using("externalEditor", function () {
StackExchange.using("snippets", function () {
StackExchange.snippets.init();
});
});
}, "code-snippets");
StackExchange.ready(function() {
var channelOptions = {
tags: "".split(" "),
id: "1"
};
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',
convertImagesToLinks: true,
noModals: true,
showLowRepImageUploadWarning: true,
reputationToPostImages: 10,
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%2fstackoverflow.com%2fquestions%2f53380612%2fsetting-learning-rate-as-negative-number-for-wrong-train-cases%23new-answer', 'question_page');
}
);
Post as a guest
Required, but never shown
active
oldest
votes
active
oldest
votes
active
oldest
votes
active
oldest
votes
Thanks for contributing an answer to Stack Overflow!
- 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.
To learn more, see our tips on writing great answers.
Some of your past answers have not been well-received, and you're in danger of being blocked from answering.
Please pay close attention to the following guidance:
- 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.
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%2fstackoverflow.com%2fquestions%2f53380612%2fsetting-learning-rate-as-negative-number-for-wrong-train-cases%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
Yes, you can. But, what would be the reason of passing a wrong ground truth to your training process?
– Neb
Nov 19 at 18:46
If I have no various data to train, I can create more data via this method to increase the certainty when I use squared error loss. But I have doubts about this method. for example lets assume we have a photo named 'X' and its label is (5,5). at first epoch, Let the model gives (2,2) for photo 'X'. if I try to train network with a photo X and label -> (4,4) using negative learning rate, it might send away the point from (2,2) to (1,1) whereas we expect it to send the point (2,2) to (5,5). Did you get what I meant?
– Faruk Nane
Nov 19 at 19:02
You are right. Using a negative learning rate and a wrong ground truth will not necessarly make the learning process converge to the optimal value for your net's parameters
– Neb
Nov 19 at 19:13
So can I say that "when I'm sure that the absolute error for each case is less than 2, I can use this method using points away 2 units." So It'll make the outputs closer to the target point. I don't really know if we can easily say that. because we consider this method as if there are only 2 parameters which is the output point. However a model has many parameters so It might affect so differently. My brain is so confused. I think this might be an academic work, right?
– Faruk Nane
Nov 19 at 19:31
Well, it is difficult to suggests you the path to follow without knowing the exact specifics of your problem. In any case, if you're trying to solve this problem for fun or self-improvement, I'd suggest you to experiment with the solutions you came up with and see if they works.
– Neb
Nov 19 at 19:34