How would I generate a Figure 8 pattern (using recurrent neural networks) using a sine wave and triangular...
I'm currently learning about Recurrent Neural Networks in my class and was assigned a homework to train a recurrent neural network. I've emailed my professor and my TA but none of them have replied since the break. I was wondering if you guys could help me understand what the input samples would be for the following statement:
"The purpose of this homework is to let you program the backpropagation through time (BPTT) algorithm to train recurrent networks. The problem is to learn by prediction a pattern in 2D space (two inputs) that will create a figure 8. Generate a sequence of samples in 2D space {x(i),y(i)} where x(i) is a triangular wave of amplitude 1/-1 and period 64 samples, while y(i) is a sinewave of amplitude 1 and period 32 samples. You can then create a periodic figure 8 easily that repeats itself. "
According to my understanding, x(i) would have samples in both x and y coordinates, but then the samples wouldn't be in 1 dimension -- they'd be in 2 dimensions. Similarly, y(i) would have 2-dimensional samples. So should I just take samples from the x-axis for the triangular wave and samples from the y-axis for the sine wave? that does not create the figure 8. Does anyone understand this statement better?
machine-learning neural-network deep-learning data-science recurrent-neural-network
asked Nov 25 '18 at 20:54
Amish SuchakAmish Suchak
6
add a comment |
I'm currently learning about Recurrent Neural Networks in my class and was assigned a homework to train a recurrent neural network. I've emailed my professor and my TA but none of them have replied since the break. I was wondering if you guys could help me understand what the input samples would be for the following statement:
"The purpose of this homework is to let you program the backpropagation through time (BPTT) algorithm to train recurrent networks. The problem is to learn by prediction a pattern in 2D space (two inputs) that will create a figure 8. Generate a sequence of samples in 2D space {x(i),y(i)} where x(i) is a triangular wave of amplitude 1/-1 and period 64 samples, while y(i) is a sinewave of amplitude 1 and period 32 samples. You can then create a periodic figure 8 easily that repeats itself. "
According to my understanding, x(i) would have samples in both x and y coordinates, but then the samples wouldn't be in 1 dimension -- they'd be in 2 dimensions. Similarly, y(i) would have 2-dimensional samples. So should I just take samples from the x-axis for the triangular wave and samples from the y-axis for the sine wave? that does not create the figure 8. Does anyone understand this statement better?
machine-learning neural-network deep-learning data-science recurrent-neural-network
asked Nov 25 '18 at 20:54
Amish SuchakAmish Suchak
6
add a comment |
I'm currently learning about Recurrent Neural Networks in my class and was assigned a homework to train a recurrent neural network. I've emailed my professor and my TA but none of them have replied since the break. I was wondering if you guys could help me understand what the input samples would be for the following statement:
"The purpose of this homework is to let you program the backpropagation through time (BPTT) algorithm to train recurrent networks. The problem is to learn by prediction a pattern in 2D space (two inputs) that will create a figure 8. Generate a sequence of samples in 2D space {x(i),y(i)} where x(i) is a triangular wave of amplitude 1/-1 and period 64 samples, while y(i) is a sinewave of amplitude 1 and period 32 samples. You can then create a periodic figure 8 easily that repeats itself. "
According to my understanding, x(i) would have samples in both x and y coordinates, but then the samples wouldn't be in 1 dimension -- they'd be in 2 dimensions. Similarly, y(i) would have 2-dimensional samples. So should I just take samples from the x-axis for the triangular wave and samples from the y-axis for the sine wave? that does not create the figure 8. Does anyone understand this statement better?
machine-learning neural-network deep-learning data-science recurrent-neural-network
asked Nov 25 '18 at 20:54
Amish SuchakAmish Suchak
6
I'm currently learning about Recurrent Neural Networks in my class and was assigned a homework to train a recurrent neural network. I've emailed my professor and my TA but none of them have replied since the break. I was wondering if you guys could help me understand what the input samples would be for the following statement:
"The purpose of this homework is to let you program the backpropagation through time (BPTT) algorithm to train recurrent networks. The problem is to learn by prediction a pattern in 2D space (two inputs) that will create a figure 8. Generate a sequence of samples in 2D space {x(i),y(i)} where x(i) is a triangular wave of amplitude 1/-1 and period 64 samples, while y(i) is a sinewave of amplitude 1 and period 32 samples. You can then create a periodic figure 8 easily that repeats itself. "
According to my understanding, x(i) would have samples in both x and y coordinates, but then the samples wouldn't be in 1 dimension -- they'd be in 2 dimensions. Similarly, y(i) would have 2-dimensional samples. So should I just take samples from the x-axis for the triangular wave and samples from the y-axis for the sine wave? that does not create the figure 8. Does anyone understand this statement better?
machine-learning neural-network deep-learning data-science recurrent-neural-network
machine-learning neural-network deep-learning data-science recurrent-neural-network
asked Nov 25 '18 at 20:54
Amish SuchakAmish Suchak
6
asked Nov 25 '18 at 20:54
Amish SuchakAmish Suchak
6
asked Nov 25 '18 at 20:54
Amish SuchakAmish Suchak
6
asked Nov 25 '18 at 20:54
Amish SuchakAmish Suchak
6
asked Nov 25 '18 at 20:54
Amish SuchakAmish Suchak
6
6
add a comment |
add a comment |
1 Answer
1
active
oldest
votes
For the {x} sample table, use function: 
For the {y} sample table, use function: 
With the 2D space {x,y}, you are generating samples using the iteration value 
.
With both of the samples {x} and {y}, you and creating them on a 1D plane in regards to the value which is what relates both equations to the sample set on the 2D space {x,y}.
answered Nov 26 '18 at 20:22
Riley CarneyRiley Carney
617316
add a comment |
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',
autoActivateHeartbeat: false,
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%2f53471874%2fhow-would-i-generate-a-figure-8-pattern-using-recurrent-neural-networks-using%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
For the {x} sample table, use function:
For the {y} sample table, use function:
With the 2D space {x,y}, you are generating samples using the iteration value .
With both of the samples {x} and {y}, you and creating them on a 1D plane in regards to the value which is what relates both equations to the sample set on the 2D space {x,y}.
answered Nov 26 '18 at 20:22
Riley CarneyRiley Carney
617316
add a comment |
For the {x} sample table, use function:
For the {y} sample table, use function:
With the 2D space {x,y}, you are generating samples using the iteration value .
With both of the samples {x} and {y}, you and creating them on a 1D plane in regards to the value which is what relates both equations to the sample set on the 2D space {x,y}.
answered Nov 26 '18 at 20:22
Riley CarneyRiley Carney
617316
add a comment |
For the {x} sample table, use function:
For the {y} sample table, use function:
With the 2D space {x,y}, you are generating samples using the iteration value .
With both of the samples {x} and {y}, you and creating them on a 1D plane in regards to the value which is what relates both equations to the sample set on the 2D space {x,y}.
answered Nov 26 '18 at 20:22
Riley CarneyRiley Carney
617316
For the {x} sample table, use function:
For the {y} sample table, use function:
With the 2D space {x,y}, you are generating samples using the iteration value .
With both of the samples {x} and {y}, you and creating them on a 1D plane in regards to the value which is what relates both equations to the sample set on the 2D space {x,y}.
answered Nov 26 '18 at 20:22
Riley CarneyRiley Carney
617316
answered Nov 26 '18 at 20:22
Riley CarneyRiley Carney
617316
answered Nov 26 '18 at 20:22
Riley CarneyRiley Carney
617316
answered Nov 26 '18 at 20:22
Riley CarneyRiley Carney
617316
617316
add a comment |
add a comment |
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.
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%2f53471874%2fhow-would-i-generate-a-figure-8-pattern-using-recurrent-neural-networks-using%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
