佐1（15题）

As machine-learning music specialist Prof Nick Bryan-Kinns explains, new neural(神经) networks are capable of writing original music — but may never — ____ meaningful lyrics（歌词）.

Music AIs use neural networks that are really large sets of bits of computers that try to ____ how the brain works.

And you can basically throw lots of music at this neural network and it learns patterns — just like how the human brain does by ____ being shown things.

What’s ____ about today’s neural networks is that they’re getting bigger and bigger, and they’re becoming harder and harder for humans to understand what they’re actually doing.

We’re getting to a point now where we have these essentially black boxes that we put music into and nice new music ____.

These neural networks also ____ a lot of energy.

If you’re trying to train AI to analyze the last 20 years of pop music, for instance, you’re ____ all that data in and then using a lot of electricity to do the analysis and to generate a new song.

There’s a little bit of ____ and mirrors going on with AI music at the moment.

You can throw Amy Winehouse’s back catalogue into an AI and a load of music will come out. But somebody has to go and ____ that.

They have to decide which parts they like and which parts the AI needs to ____ a bit more.

The problem is that we’re trying to train the AI to make music that we like, but we’re not ____ it to make music that it likes.

I’m also kind of ____ that one as well.

Lyrics for songs are typically based on lyricists’ ____, what’s happened to them.

Lyricists write about falling in love, things that have gone wrong in their lives, or simple ____ like watching the sunrise.

I’m not sure that an AI will have that potential to be able to ____ something meaningful to people.