MIT6_047f08_rec03 - MIT OpenCourseWare http/

Info iconThis preview shows pages 1–3. Sign up to view the full content.

View Full Document Right Arrow Icon

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
This is the end of the preview. Sign up to access the rest of the document.

Unformatted text preview: MIT OpenCourseWare 6.047 / 6.878 Computational Biology: Genomes, Networks, Evolution Fall 2008 For information about citing these materials or our Terms of Use, visit: . 6.047/6.878 Fall 2008 Recitation 3 Notes Pouya Kheradpour September 19, 2008 1 Practical issues of machine learning There are many practical issues to deal with when performing machine learning. This is especially true in computational biology because the data sets are so complex that you have to be very careful that your results are meaningful. 1.1 Overfitting 1. In lecture we saw the example of having many clusters leading to a higher probability of the data. 2. This is an extremely, generally unavoidable problem with machine learning – more parameters leads to better training performance. 3. Using more parameters/features generally leads to more overfitting. (a) Always consider how much data you have and if it is enough to learn all the parameters your model has. If you have more features, it may be more likely that the classifier finds something that separates the data just by chance....
View Full Document

This note was uploaded on 09/24/2010 for the course EECS 6.047 / 6. taught by Professor Manoliskellis during the Fall '08 term at MIT.

Page1 / 3

MIT6_047f08_rec03 - MIT OpenCourseWare http/

This preview shows document pages 1 - 3. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online