Hacker News new | past | comments | ask | show | jobs | submit login

One of the cofounders of the Echonest (acquired by Spotify) created this back in 2004:

    "A Singular Christmas" was composed and rendered in 2004. It is the automatic statistical distillation of hundreds of Christmas songs; the 16-song answer to the question asked of a bank of computers: "What is Christmas Music, really?"


Very interesting reference! Deep learning is statistical, so this is sorta one of the spiritual predecessors.

By my understanding, yes, in the sense that certain parts of each algorithm are looking to minimize something...the former model used principal components analysis, which is linear in the sense that you are using transforms which pick out for the least correlated pieces of a huge chunk of data, whereas neural networks, which uses a combination of linear and non-linear layers picked by the user to minimize, "errors."

What's interesting is that the former model sounds so much, "better." I wonder if anyone could chime in about how our ears and auditory nerves or perhaps auditory cognition works, and whether they are more, "principal component analysis-y" somehow than "error minimization-y" or something relating to the actual math, which may explain why this new neural network christmas song sounds like absolute crap to us, whereas the older version sounds pretty amazing. Also, whether my understanding of the underlying math is correct or not.

Guidelines | FAQ | Support | API | Security | Lists | Bookmarklet | Legal | Apply to YC | Contact