Welcome to the world of Gnod
I wish there was a learning Computer Prog that I could use to find new Bands, wait I’ve found it;
another part of Gnod is
http://www.music-map.com/
Type a band ya know and it’ll map out similar bands….
Gnod explained;
Gnod is my experiment in the field of artificial intelligence. Its a self-adapting system, living on this server and ‘talking’ to
everyone who comes along. Gnods intention is to learn about the outer world and to learn ‘understanding’ its visitors.
This enables gnod to share all its wisdom with you in an intuitive and efficient way. You might call it a search-engine to
find things you don’t know about.
I hope this site brings sum new Bands into your life, it worked for me……………………
n0mad
Sub Dub Micromachine new album is out it’s called – Auferstanden
Padman music by the Padman artists
Comments
i tested this
from someone whom has a rather bizare and ranged taste in music but only likes a few bands i set this program a rather had task.
ill say from the results Ive found it has a 3 from 5 chance of getting it right.
But i did sit down and think about it and how it works. its fairly simple in theory. if i select a band which is classed as “acid jazz / funk” the program throws out a list of other bands listed under the same genre.
theories aside, it works reasonably well. give it a go
Not so simple
> But i did sit down and think about it and how it works. its fairly simple in theory…
It’s actually using some fairly tricky AI learning techniques. What you’ve presented is simple deductive reasoning from a rule, wheras Gnod uses inductive reasoning from collected data. The difference is that you (a human) had to invent the rule, whereas Gnod can learn it’s own rules. The end result is similar enough, but the process taken to get there is profoundly different. Plus the process can be repeated for all sorts of stuff.
I have a friend who works with neural networks (a simple learning algorithm) to professionally bet on horse races. In this way the computer can learn from ongoing results that “Silver Sovereign runs well in the wet on a Monday when the jockey is a woman” without a human telling them to use this rule. The best stock market analysis and recommendation tools are similar in design.
Personally I think the practical service of music recommendation is provided better by http://lastfm.com which I guess uses the same kind of stuff used by Amazon recommendations. Item-to-item Collaborative Filtering: http://www10.org/cdrom/papers/519/. Most recommendation engines are based on this technique.
(end of computer science geekery)
last.fm
Was gonna recommend last.fm too, but for much less scientific reasons…. you can listen to the music it recommends for free (which gnod may or may not let you do, haven’t checked it out yet)
Post new comment