Name: ml5: ニューラルネットワーク回帰 (ml5: Neural Network Regression)
Uploaded: 2021-01-14T10:18:11.000Z
Duration: 9 min 51 s
Description: VoiceTubeの動画で発音を聞きながら英語表現を覚えよう！学べる英語：

仮定法過去

but if you didn't arrive from the previous videos

you might feel a little bit lost because what I'm going to do

here entirely depends on the previous few videos

where I trained model to classify musical notes based

is change this word from classification--

I'm going to do it right now-- to regression,

what the neural network outputs and how I use that output.

But before I start changing anything else in the code,

let me talk about what I mean by regression in the context

The idea of classification is that the neural network

is going to receive some input and end up

meaning it's going to assign a label C, D, or E.

We can think of that as there's three light bulbs.

Are those like little drawings of light bulbs?

Each light bulb is associated with one of the possible labels

that this particular input corresponds to the label E,

then maybe this light bulb would light up.

You could build an Arduino with some LEDs

and have the results of the machine learning classification

A regression, you could think of the output

As the data comes into the neural network,

the dial ends up at some value between some minimum

The output is numerical continuous output.

So classification is one of a discrete set of possibilities,

and regression is any value between a given range.

Now you can still have multiple outputs in a regression

because you can have multiple continuous values,

but in this case, I want to redo this example

by having a single output and that output

now I want my output to be tied to a frequency.

No longer do I want during the training process

will get the number as part of the regression output.

When I click the mouse, the inputs are in x and y,

But I don't want it to be a target label anymore.

And I can figure out what that target frequency

is by looking it up in this particular JavaScript object.

So I can say let target frequency equal notes

something that I'm already doing down here.

So let's replace this with target frequency.

Now, ordinarily, I might remove target label

for the machine learning model, not using CDE and not

using the note name for training the model.

I still would like to see the note C or A or G

because I think that's less awkward than drawing

done with all that I need for the first two steps--

the first two steps being collect the data

and now I obtained the output to a single output node that

So I should be able to run all of the bits of code

that I did before and have a train the model.

All right, collected some data-- let's train the model.

didn't don't see any errors in the console,

and I see a nice graph with the loss going all the way down.

Incidentally, the lost went way down very, very quickly.

Maybe this regression problem is a little bit easier for it

So now that collecting data and training the model is done,

I need to just do that last stage of basically deploying

the model and making predictions with new data.

It's still looking for a label and all that.

First of all, it's writing the word frequency here and just

字幕リスト動画再生

ml5: ニューラルネットワーク回帰 (ml5: Neural Network Regression)

stuff

bunch

sophisticated

multiple