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

Link to this comparison view

Both sides previous revision Previous revision
Next revision
Previous revision
mind:log-entries [2017/04/06 12:53]
mind:log-entries [2017/05/20 02:53] (current)
Line 1: Line 1:
 =Log= =Log=
-==April 6, 2017==+==May 19,2017== 
 ===To Do=== ===To Do===
 +* Perhaps should be weighted max clique and not maxclique with weight as secondary measure
 +* Favor big cliques as opposed to long matches
 +* Figure out how to include local maxima representing even short tagline choruses in the max clique calculations
 +* Ignore non-word vocalizations via dictionary? (this could be one of the "​flavors"​ of the algorithm)
 +* Use phrase breaks to determine chorus end (and maybe beginning) (this could be another "​flavor"​)
 +* Label more data
 +* Introduce more parameters (use multi-venn diagram to show accuracy as combination of features)
 +* Do it all over for verses
 +* Axon Website
 +** link to pierre
 +** link to CV
 +** link to LinkedIn
 +** link to Google Scholar profile
 +** photos from grad poster thing
 +** grad poster thing
 +** video from Asher
 +** video from grad student society about me
 +** videos about bioinformatics discovery
 +** all pubs with links
 +** blog
 +* Decompress all of the mxl files, make changes directly to mxl files, starting with Michael Bublé, maybe even incorporate annotations that way (input them the same way I'm outputting them)?
 +* Don't normalize aln matrices—pick static value as min threshold (actually let the GA decide it)
 +* Make the minDistanceFromDiagonal a parameter to be learned
 +* Implemented Generic self-similarity alignment
 +* Thoroughly annotated Twinkle and Rainbow for any repetition in any viewpoint
 +* Use F-Score instead of accuracy for fitness function
 +* Implement it for pitch, harmony, and lyrics
 +==May 5, 2017==
 +* In the case of ties, use the one with the higher score
 +* Find faster implementation of max clique solution
 +* Why not "​Honesty"?​ (I was writing over it with other billy joel song: solution was to not substr file name)
 +==May 4, 2017==
 +* Make website
 +* Revise and resubmit ICCC paper
 +* Implement alignment module for xmls
 +* Implement genetic algorithm for finding params
 +* Figure out how to label tagline choruses: solution was to actually label them as tagline choruses. Might have repercussions down the road when running Pop*.
 +* Implement mechanism for identifying multiple choruses: solution was to find local maxima and do max clique to find mutually agreeing choruses
 +==April 10, 2017==
 +Work on alignment paper
 +* Compute all the events to be aligned up front instead of recomputing them on the fly—duh
 +* Make the computation more effective by linearly traversing data structure instead of repeatedly computing access point, too
 +* Keep testing that correct elements are being aligned
 +** NOTE: aligning lyrics requires having the right lyrics (e.g., multiple verses represented using repeat signs). Having the right lyrics (as of now) requires knowing the segment type (i.e., choruses, you take whatever lyrics are there for each note; verses have to use lyrics that match the repeat count). We need to implement something that doesn'​t require knowing the segment type to infer whether any lyric will work or whether it has to be the lyric matching the repeat count of surrounding lyrics. OR just use the manually labeled segment type to extract lyrics from XML. This isn't cheating because it's really a different problem.
 +==April 6-7, 2017==
 +Work on alignment paper
 +* Finish alignment module
 +* Test that correct elements are being aligned
 +Process Qualtrics data
 +* Download data
 +* Find script to process data
 +* Process accuracy and confusion matrix
 Make Pop* run deterministically Make Pop* run deterministically
 * Create a global random number generator seed in the program args or configuration setting * Create a global random number generator seed in the program args or configuration setting
Line 7: Line 72:
 * If that doesn'​t work, fix each one individually * If that doesn'​t work, fix each one individually
 * Check that it works to rerun multiple times with same output * Check that it works to rerun multiple times with same output
-Process Qualtrics data 
-* Download data 
-* Find script to process data 
-* Process accuracy and confusion matrix 
-Work on alignment paper 
-* Finish alignment module 
-* Test that correct elements are being aligned 
-* Implement linear perceptron 
-* Run regression 
 Finish Doctoral Consortium Paper Finish Doctoral Consortium Paper
 * Add 4 references * Add 4 references
mind/log-entries.1491504803.txt.gz · Last modified: 2017/04/06 12:53 by norkish
Back to top
CC Attribution-Share Alike 4.0 International
chimeric.de = chi`s home Valid CSS Driven by DokuWiki do yourself a favour and use a real browser - get firefox!! Recent changes RSS feed Valid XHTML 1.0