| Line 6: | Line 6: | ||
=Third Homework, [[ECE662]] Spring 2012= | =Third Homework, [[ECE662]] Spring 2012= | ||
| − | + | *Drop test set output, predicted accuracy, and proposed nickname into [https://www.projectrhea.org/rhea/index.php/Special:DropBox?forUser=drugeles&assn=true Daniel's drop box] before 11:59pm, Friday April 27, 2012. | |
| + | *Report due before 11:59pm, Monday April 30, in [https://www.projectrhea.org/rhea/index.php/Special:DropBox?forUser=mboutin&assn=true your instructor's Rhea dropbox]. '''Make sure to drop it in the correct homework folder!!!!'''. It is the one at the very bottom of the page. | ||
---- | ---- | ||
==Automatic Pattern Recognition Contest!== | ==Automatic Pattern Recognition Contest!== | ||
An anonymous company has agreed to share real data with us, so we are going to have a little contest using this data! The data comes from a five-class classification problem using 13 features. We are looking for the student who will design the most accurate classifier using this data. | An anonymous company has agreed to share real data with us, so we are going to have a little contest using this data! The data comes from a five-class classification problem using 13 features. We are looking for the student who will design the most accurate classifier using this data. | ||
| − | The [[training_data_HW3_ECE662S12|training data]] consists of 550 data points (i.e. 550 points in a 13 dimensional space) along with the correct label for each point. Use this data, along with any method of your choice, to design what you think is an accurate classifier | + | The [[training_data_HW3_ECE662S12|training data]] consists of 550 data points (i.e. 550 points in a 13 dimensional space) along with the correct label for each point. Use this data, along with any method of your choice, to design what you think is an accurate classifier. |
| − | + | ==Part I== | |
| + | When you are done designing your classifier, write down what accuracy the classifier has, according to the training data. (This is what we call the "predicted accuracy".) Then use your classifier to classify the following [[test_data_HW3_ECE662S12|test set vectors]]. Daniel has kindly volunteered to collect all the answers and summarize their accuracy in the table below. In order for Daniel to do that, we ask that you send him | ||
| + | *The nickname you want him to use to identify your work in the table below; | ||
| + | *Your predicted accuracy; | ||
| + | *The labels you obtain for each test set vector. | ||
| + | Hand in everything in [https://www.projectrhea.org/rhea/index.php/Special:DropBox?forUser=drugeles&assn=true Daniel's drop box] following this syntax: | ||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
| − | |||
<p> | <p> | ||
Joe Blo<br /> | Joe Blo<br /> | ||
| Line 42: | Line 39: | ||
<br /> | <br /> | ||
| + | ==Part II== | ||
| + | After the deadline for the homework has passed, I will release the ground truth labels for the test set vectors [[test_data_labels_HW3_ECE662S12|here]]. (If you are done designing your classifier before midnight on Thursday April 26, you may obtain the ground truth labels by emailing your instructor.) Compare the labels obtained using your classifier with the ground truth labels: the number of correctly classified vectors is the "test" accuracy. Report test your classifier on the testing data and note its accuracy. Summarize your method and results in a report. | ||
| − | + | ==Part III (optional)== | |
| − | + | If you feel like sharing your results and methods publicly, feel free to post a summary of your method and replace your nickname by your true name in the table below. But please only do this '''after the deadline for the homework has past'''. If you do not wish to be identified, but still would like a summary of your method to appear below, send it to Daniel (by email) and he will post it for you. | |
| − | + | ||
| − | + | ||
| − | + | ---- | |
| + | The discussion page for this homework is [[hw3_discussion_ECE662_S12|here]]. | ||
| + | ---- | ||
---- | ---- | ||
==Result Summary== | ==Result Summary== | ||
| − | This results will be computed from the submissions in drugeles dropbox. Refer to All versus All Classification section. | + | This results will be computed from the submissions in [https://www.projectrhea.org/rhea/index.php/Special:DropBox?forUser=drugeles&assn=true drugeles dropbox]. Refer to All versus All Classification section. |
{| | {| | ||
! style="background: rgb(238, 238, 238) none repeat scroll 0% 0%; -moz-background-clip: -moz-initial; -moz-background-origin: -moz-initial; -moz-background-inline-policy: -moz-initial;" colspan="4" |column labels go here | ! style="background: rgb(238, 238, 238) none repeat scroll 0% 0%; -moz-background-clip: -moz-initial; -moz-background-origin: -moz-initial; -moz-background-inline-policy: -moz-initial;" colspan="4" |column labels go here | ||
| Line 58: | Line 57: | ||
|Nickname (add link to method summary or report) | |Nickname (add link to method summary or report) | ||
|Confusion Matrix | |Confusion Matrix | ||
| − | | | + | |Test Set Accuracy |
|Predicted Accuracy | |Predicted Accuracy | ||
|- | |- | ||
Revision as of 09:37, 20 April 2012
Contents
Third Homework, ECE662 Spring 2012
- Drop test set output, predicted accuracy, and proposed nickname into Daniel's drop box before 11:59pm, Friday April 27, 2012.
- Report due before 11:59pm, Monday April 30, in your instructor's Rhea dropbox. Make sure to drop it in the correct homework folder!!!!. It is the one at the very bottom of the page.
Automatic Pattern Recognition Contest!
An anonymous company has agreed to share real data with us, so we are going to have a little contest using this data! The data comes from a five-class classification problem using 13 features. We are looking for the student who will design the most accurate classifier using this data.
The training data consists of 550 data points (i.e. 550 points in a 13 dimensional space) along with the correct label for each point. Use this data, along with any method of your choice, to design what you think is an accurate classifier.
Part I
When you are done designing your classifier, write down what accuracy the classifier has, according to the training data. (This is what we call the "predicted accuracy".) Then use your classifier to classify the following test set vectors. Daniel has kindly volunteered to collect all the answers and summarize their accuracy in the table below. In order for Daniel to do that, we ask that you send him
- The nickname you want him to use to identify your work in the table below;
- Your predicted accuracy;
- The labels you obtain for each test set vector.
Hand in everything in Daniel's drop box following this syntax:
Joe Blo
77%
1
0
1
2
3
4
2
3
1
2
0
2
1
Part II
After the deadline for the homework has passed, I will release the ground truth labels for the test set vectors here. (If you are done designing your classifier before midnight on Thursday April 26, you may obtain the ground truth labels by emailing your instructor.) Compare the labels obtained using your classifier with the ground truth labels: the number of correctly classified vectors is the "test" accuracy. Report test your classifier on the testing data and note its accuracy. Summarize your method and results in a report.
Part III (optional)
If you feel like sharing your results and methods publicly, feel free to post a summary of your method and replace your nickname by your true name in the table below. But please only do this after the deadline for the homework has past. If you do not wish to be identified, but still would like a summary of your method to appear below, send it to Daniel (by email) and he will post it for you.
The discussion page for this homework is here.
Result Summary
This results will be computed from the submissions in drugeles dropbox. Refer to All versus All Classification section.
| column labels go here | ||||
|---|---|---|---|---|
| Position | Nickname (add link to method summary or report) | Confusion Matrix | Test Set Accuracy | Predicted Accuracy |
| 5 | Joe Blo (method summary) | $ \left( \begin{array}{cccccc} &\mathbf{0}&\mathbf{1}&\mathbf{2}&\mathbf{3}&\mathbf{4}\\ \mathbf{0}& x& x& x& x& x \\ \mathbf{1}& x& x& x& x&x \\ \mathbf{2}& x& x& x& x&x \\ \mathbf{3}& x& x& x& x& x\\ \mathbf{4}& x& x& x& x&x \\ \end{array} \right) $ | 75% | 77% |
Back to ECE 662 Spring 2012
