Friday, August 8, 2008

Introducing: Fuzzy Biases

Suppose you're really into music created around the "summer of love" in 1967. Its easy enough it create a filter so you only get music from 1967. We could do that in Amarok 1, but that excludes a lot of music around that period that's just as significant.

Maybe you could do something like asking for everything that's recorded after 1960 but before 1973. That's better, but it's still not really what you mean when you say around 1967. You would prefer tracks closer to 1967 than farther away.

This is where "fuzzy biases" come in. The goal with fuzzy biases, is create a playlists that approximately match a value. Generating biased playlists, is always a question of probability distributions. What we are really trying to do here is generate a playlist that fits normal distribution bell-curve.

Like this:

The horizontal axis is the year, the vertical axis is the probability of getting track of that particular. So the nearer to 1967 the track is, the better chance of it ending up in our playlist it has.

Ok, another example.

I really just want to listen to some good straight up pop right now. No eleven minute epic folk ballads, no classical, no post-rock, just tight catchy songs. So I make a fuzzy bias to find songs that are about three minutes long.

Great. That's a pretty good mix, and I can refine it later with other biases.

The fairly vague "Strictness" slider indirectly controls the standard deviation of of the distribution.

It looks a little like this:

How is this different than the old fashion method, just specifying a pair of strict biases?

To get all mathematical on you, that creates a playlist that matches a uniform distribution.

If you've never taken a statistics class and didn't follow any of this, let me summarize:

  1. pretty curves > boring rectangles.
  2. Apparently a math degree is actually good for something.
  3. Mom, you owe me an apology.


Marcel said...

Nice feature, although (as an album lsitener) I'll never use it...

However, could you please label the 2 options in a way that even people without a math degree can understand what a "proportional bias" and a "fuzzy bias" is good for? ;)

Uhm, yeah. Thanks for your work on Amarok! :)

Parker said...

I love the summary.

reldruH said...

What a wonderful summary, much easier to understand than all those confusing pictures :-) I just have a couple questions: what criteria will we be able to use for these fuzzy biases? I'm assuming all the amarok metadata will be available but what about more abstract things, like tempo (is there a way to even calculate that?) or using moodbar information? Similar artist information is available from, will we be able to have a fuzzy bias of '50% similar to Tom Petty' and '50% upbeat music'? Also, what if I'm looking for a range (of years, possibly) with strict endpoints (nothing outside that range)? Does that require two biases? One for the lower bound, one for the upper bound or is there the ability to do that in one bias? Can't wait to try it out. Thanks for putting all the work in for this. Dynamic playlists were never that great for me but this like it'll be really useful.

tbocek said...

@reldruh, I've taken a very general look at the bias framework and it's very general - you could implement a bias for tempo (although having the tempo cached in the files would probably be a necessity for this to work) or anything else like that. I'm looking into implementing a bias that allows you to match Nepomuk tags (the tags you assign in Dolphin), although I can't quite figure out the framework well enough

Anonymous said...

we offer wow power leveling and wow gold wow gold

Anonymous said...

I like the graph you have created here. I'm looking forward for your next blog to see how it goes again. Company Logo Design

Admin said...

There Is Obviously a lot to know about this. I suppose you made Some Great points in the Feature also.
Custom Logo Design

Admin said...

Verry nice weblog and useful! I feel i will come back one day !

Houston Search Engine Optimization

rohit mathpal said...

It was a wonderful chance to visit this kind of site and I am happy to know. thank you so much for giving us a chance to have this opportunity! I will be back soon for updates.
San Francisco Limo

Admin said...
This comment has been removed by the author.
Admin said...

Thanks for this article. It's just what I was searching for. I am always interested in this subject.
Aerospace Logo

Sophia White said...

A great site regarding creativity and also enhances knowledge, I'm assuming good feedback is allowed too but here it is either way. I just wanted to say, I'm a beginner in IT field. I wish I could make sites like these favorites. I don't know who makes these websites but you guys are great. I really like that kind of attention to detail.Great job on the websites and stuff, hope to see more of you guys work in the future.
Business VoIP

Syed Faizan said...

This is nice-looking very interesting. I actually never thought I could have a good read by this time until I set up out this forum. I am thankful for the given particular information. Pakistani Models

Felix Smith said...

A great post, thanks for taking the time to share, continued success to your site in the future! GOOD Work. Paper Writing Services

Felix Smith said...
This comment has been removed by the author.
Felix Smith said...

I always enjoy reading such posts which provide knowledge based information like this blog. Keep it up. Cheap Essays

Felix Smith said...

Excellent site, keep up the good work my colleagues would love this. Cheap Essay Writing
Professional Essay Writing
Dissertation Writing Services
Thesis Writing Services
College Essay Writing

Fabian Smith said...

Really rich content and very useful information. I found my problem’s solution starting over here. Custom Essays

Mia Smith said...

This is a really good site post, i am delighted I came across it. Coupon Missy
Coupon Codes
Free Shipping
Grocery Coupons
Haggar Coupons
Home Depot Coupons
HSN Coupons
JcPenney Coupons
Kohls Coupons
Kmart Coupons
Light In The Box Coupons
Loccitane Coupons
Macys Coupons
Meijer Coupons
New Egg Coupons
Next Day Flyers Coupons
Nine West Coupons
Old Navy Coupons
Overstock Coupons
Perfumania Coupons
Perry Ellis Coupons
P.S. from Aeropostale Coupons
QVC Coupons
Redplum Coupons Coupons
Safeway Coupons
Saks Coupons
Sams Club Coupons
Sears Coupons Coupons
SmartBargains Coupons
SmartSource Coupons
Target Coupons

david paul said...

Happy to see this, I am happy to find this great Blog.
Custom Essays

david paul said...

Must agree that you are one of the best bloggers I ever saw.

zachray taylor said...

custom essays
I loved the way you discuss the topic great work thanks for the share.

lelle sandy said...

cheap essays
Very impressive and informative thanks for the great post.

sophia martin said...

Cheap Essays
Wow Amazing post really informative thanks for the great post.

zachray taylor said...

custom essays
I loved the way you discuss the topic great work thanks for the share.

jacqueline fernandez said...

Amazing work i like your idea how you discuss each and every thing related to this blog.
SEO Company

sophia martin said...
This comment has been removed by the author.
sophia martin said...

This was a great and interesting article to read. I found many interesting things from this site. It helps me many way.
Cheap Essay

zachray taylor said...

Wow amazing stuff I really enjoyed thanks for the amazing stuff.
Cheap Essays