User Tools

Site Tools


people:kidson:machine_learning

Differences

This shows you the differences between two versions of the page.

Link to this comparison view

people:kidson:machine_learning [2012/10/28 12:49]
kidson created
people:kidson:machine_learning [2012/10/28 15:59] (current)
kidson
Line 1: Line 1:
-Machine Learning- Musical note pitch recognition+====== ​Machine Learning- Musical note pitch recognition ​======
  
 The aim of this project was to use machine learning approaches to classify the pitch of notes played from an instrument. ​ The ultimate goal was to convert a recorded piece into a script. The aim of this project was to use machine learning approaches to classify the pitch of notes played from an instrument. ​ The ultimate goal was to convert a recorded piece into a script.
Line 8: Line 8:
  
 Logistic regression and Support Vector Machine algorithms were implemented. ​ Logisitic regression showed to be more accurate, achieving up to 90% classification accuracy on slow music. Logistic regression and Support Vector Machine algorithms were implemented. ​ Logisitic regression showed to be more accurate, achieving up to 90% classification accuracy on slow music.
 +
 +{{:​people:​kidson:​machine_learning:​music.jpg?​500|}}
 +
 +==Links==
 +
 +{{:​people:​kidson:​machine_learning:​musical_pitch_detection.pdf|Final Report}}
 +
 +Sorry I don't have the code online for this one.  This was programmed using octave, and [[http://​www.csie.ntu.edu.tw/​~cjlin/​libsvm/​|LibSVM]] was used for the SVM part.  If you are interested don't hesitate to contact me: ross.kidson at gmail.com
people/kidson/machine_learning.1351424985.txt.gz · Last modified: 2012/10/28 12:49 by kidson