I want to make this hit.

Whenever you upload a song to that site it goes directly to Timberland's desktop. Then he "samples" it and makes it a "hit."

winrar!

The Manual by The KLF?

Yes I do believe that is the one

Obviously it's not a "hit" by definition until it's on the radio and charting and all that but it seems this simply compares your shit to the shit that already did that

The Manual by The KLF?

I actually was so thinking about the The KLF's The Manual, but seeing that the OP was about AI, I just thought it was too off-topic.

Thanks for the schooling, µB. Neural Networks is something that always attracted my attention since I was a kid and it's always cool to learn more about the current developments

I can't remember their name but there was a band back in the day that sometime during their career decided they wanted to step away from their usual writing style briefly and focus on writing a song that would almost certainly be a number one on the charts.

So they did, and it was, and they wrote a book about it called "How To Write A Number One Hit", and some band in sweden or somewhere went by the book, literally, and also managed to pen a number one single. Pretty rad if you ask me.

The idea that a trained neural network could compare input to it's 'perfect' template and then calculates the overlap is viable, but probably not practical (yet). That seems to be what they're offering from what I've read, and a comparison with the DB of the neural network would be very quick (The dissection of the input data should however take a while depending on the width of parameters). The accuracy of the result depends on how well the network was trained, how many aspects of the input are compared and human-made adjustments for exceptions, training errors and such.

So, yes, it could work to a degree. I'd file this particular site under 'toy' though, because I have yet to see a neural network that was trained so well that it could tackle a complex beast like the effect of music on the human brain*, mainly because we still haven't figured out how exactly our brain works. There were some interesting efforts in combining genetic algorithms (evolution based self-writing networks) with AI last I checked on the topic, and complex tasks in areas that are explained well (ie we know most of the system parameters) can be solved. For example, a few years ago a trained network was able to perform the landing operation of a jet.

*) See for example the yet unsuccessful attempts of using neural networks as a translation tool. Language is comparable to music in width of parameters and complexity

Edit:Fixed some Germanglish

And yes, that site is pretty far feetched. lol

akira^8GB wrote:

What a load of bullshit!

Which is bullshit:

A) the notion that a computer can compare song data to see if it has characteristics of other hit songs or
B) that website? (im guessing this one)

Both, man!
Just the fact that it has "characteristics" of other hit songs doesn't mean it will be a hit. I can copy how a Snoop Dogg song is and it could not be a hit! Also, this will depend on socio/geographical factors.

A website existing that offers this "service" is 10x more bullshit

Hilarious link of the week!

Whenever you upload a song to that site it goes directly to Timberland's desktop. Then he "samples" it and makes it a "hit."

LOL 10 points for Oxy