LFD Book Forum numerical issues

#1
01-18-2013, 04:04 PM
 geekoftheweek Member Join Date: Jun 2012 Posts: 26
numerical issues

On questions 5, 6, 7 I keep getting answers that are about half way between two possible values. The answers I'm getting make sense to me and because they are not *exactly* halfway between the two answers I am technically able to find a closest value, but that's just chance. I expect that the options are all way off except one right? But that's not what I'm seeing.

For instance, if there are two options: 1 and 10, I might get a value of 5. Yes, 5 is closer to 1 than 10 but not by much, and it's making me have no confidence in my answers.

If we are getting answers that are sort of on the fence like this does that imply that they are dead wrong? Please advise.

Thanks
#2
01-18-2013, 04:51 PM
 sanbt Member Join Date: Jan 2013 Posts: 35
Re: numerical issues

Quote:
 Originally Posted by geekoftheweek On questions 5, 6, 7 I keep getting answers that are about half way between two possible values. The answers I'm getting make sense to me and because they are not *exactly* halfway between the two answers I am technically able to find a closest value, but that's just chance. I expect that the options are all way off except one right? But that's not what I'm seeing. For instance, if there are two options: 1 and 10, I might get a value of 5. Yes, 5 is closer to 1 than 10 but not by much, and it's making me have no confidence in my answers. If we are getting answers that are sort of on the fence like this does that imply that they are dead wrong? Please advise. Thanks
For 5 and 6, it's possible that the result is almost halfway between 2 answers, but it should always favor one answer.
#3
01-20-2013, 01:39 AM
 gah44 Invited Guest Join Date: Jul 2012 Location: Seattle, WA Posts: 153
Re: numerical issues

Quote:
 Originally Posted by geekoftheweek On questions 5, 6, 7 I keep getting answers that are about half way between two possible values. (snip) For instance, if there are two options: 1 and 10, I might get a value of 5. Yes, 5 is closer to 1 than 10 but not by much, and it's making me have no confidence in my answers. If we are getting answers that are sort of on the fence like this does that imply that they are dead wrong? Please advise. Thanks
If you repeat the experiment 1000 times, and average, it is more and more unlikely that you get the wrong closest answer.

If you are still unsure, do another 1000 times and verify that it is still the same.

For problems where the answer is an integer , the standard deviation is and the standard devation of the mean of trials is the standard deviation divided by , or .

To be reasonably sure, you should be a few standard deviations away from half way.

 Thread Tools Display Modes Linear Mode

 Posting Rules You may not post new threads You may not post replies You may not post attachments You may not edit your posts BB code is On Smilies are On [IMG] code is On HTML code is Off Forum Rules
 Forum Jump User Control Panel Private Messages Subscriptions Who's Online Search Forums Forums Home General     General Discussion of Machine Learning     Free Additional Material         Dynamic e-Chapters         Dynamic e-Appendices Course Discussions     Online LFD course         General comments on the course         Homework 1         Homework 2         Homework 3         Homework 4         Homework 5         Homework 6         Homework 7         Homework 8         The Final         Create New Homework Problems Book Feedback - Learning From Data     General comments on the book     Chapter 1 - The Learning Problem     Chapter 2 - Training versus Testing     Chapter 3 - The Linear Model     Chapter 4 - Overfitting     Chapter 5 - Three Learning Principles     e-Chapter 6 - Similarity Based Methods     e-Chapter 7 - Neural Networks     e-Chapter 8 - Support Vector Machines     e-Chapter 9 - Learning Aides     Appendix and Notation     e-Appendices

All times are GMT -7. The time now is 09:41 AM.