ADM-201 dump PMP dumps pdf SSCP exam materials CBAP exam sample questions

【人工智能实验系列】无穷打鼓机 – 译学馆
未登录,请登录后再发表信息
最新评论 (0)
播放视频

【人工智能实验系列】无穷打鼓机

A.I. Experiments: The Infinite Drum Machine

【人工智能实验系列】无穷打鼓机
[AI Experiments: The Infinite Drum Machine]
嘿 我是卡尔
Hey, I am kyle.
我是Annie 嗨 我是Yotam
I am Annie.Hi, I am Yotam.
【程序猿兼音乐人】(╯3╰)
[coders / musicians]
这是我们做的无穷打鼓机
This is something we made called infinite drum machine.
这主要是一个关于机器学习如何组织每天声音的实验
It’s basically an experiment to see how machine-learning might organize everyday sounds.
那么 任何曾经和声音打交道的人能看出为什么这很难
So anyone who’s ever had to work with a lot of sound can see why this is hard.
比如 我们都能听到这个和这个很相似
For example,we can all hear that this is similar to this
但是完全和这个不一样
but totally different from this.
但是很难说清楚为什么 因为声音很复杂
But it’s hard to articulate exactly why, because sounds are complicated.
但这正是机器学习所擅长的
But this is kind of thing that machine learning is really good at.
我们做了个小实验
So we ran a little test.
我们输入电脑上千种声音
We played thousands of sounds for the computer.
我们没有给声音描述 标签
We didn’t give it descriptions or tags
或任何人们通常组织声音的提示
or any hints on how people usually organized sound.
我们想知道它是否能听这些声音
We wanted instead to see if could listen to them
并且自动学习自己的方式来组织他们
and automatically learn its own way to organize them.
这个实验用了一种技术叫做t-SNE
This experience uses a technique called t-SNE.
首先电脑会为每个样本制作一个指纹
First the computer creates a fingerprint from each sample,
像一张图片或一系列的数字来代表特定的声音
which is like an image or a set of numbers that represents that particular sound.
然后t-SNE比较所有的指纹并把相似的声音放在一起
Then t-SNE compares all the fingerprints and places similar sounds close together.
一种想象t-SNE的方法是
One way to think about t-SNE is that
它从高纬度空间采集这些指纹
it’s taking these fingerprints from high dimensional space,
也就是这空间超过三维
which means the space is more than three dimensions
然后将他们减少到二维
and reducing them in this case to two dimensions
这样我们才能可视化它
so that we can visualize it.
我们的测试基本成功
And our test basically worked.
这就是我们得到的t-SNE
This is a t-SNE that we got.
我们将它放在网上让所有人来试验
We put it on the web so anyone can play with it.
你可以得到这些临近的相似的声音
You get these neighborhoods of similar sounds
可以拖动他们来探索
that you can explore by dragging around.
或者用这个打鼓机敲打他们
And may beat with them by using this drum machine.
我们希望人们发现它有趣
We are hoping people find it fun,
不论你是想探究机器学习
whether you are more into the machine learning side
还是想做音乐
or more into making music.
都可以从G.CO/AIEXRIMENTS网站获得源码来自己试试
You can play with it and get the code at G.CO/AIEXPERIMENTS.

发表评论

译制信息
视频概述
听录译者

(B)Z

翻译译者

(B)Z

审核员

知易行难

视频来源

https://www.youtube.com/watch?v=9x-_My5yjQY

相关推荐