Name: ml5.js：用像素作為輸入來訓練神經網絡。 (ml5.js: Train a Neural Network with Pixels as Input)
Uploaded: 2021-01-14T10:52:30.000Z
Duration: 18 min 38 s
Description: 【看影片學英語】數萬部 YouTube 影片，搭配英漢字典即點即查，輕鬆掌握單字發音與用法，長久累積看電影不必再看字幕。

基礎被動語態

And you thought we were done with the ML5 neural network

There is one more because I am leading to something.

I am going to-- you will soon see in this playlist

a section on convolutional neural networks.

But before I get to convolutional neural networks,

I want to look at reasons why a convolutional layer.

I have to answer this question like, what is a convolution?

But before I get to that, I want to just see why

there saying to yourself, you've done videos

was about using a pre-trained model for an image classifier.

That pre-trained model had convolutional layers in it.

So I want to now take the time to unpack what that means more

and look at how you could train your own convolutional neural

about how we would make an image classifier

And that image is being sent into an ML5 neural network.

And out of that neural network comes either a classification

And in fact, we could do an image regression.

because I think it's a lot simpler to think about

So maybe it comes out with one of two things,

either a cat or a dog and some type of confidence score.

I previously zoomed in on the ML5 neural network

We have this hidden layer with some number

of units and an output layer, which, in this case,

would have just two if there's two classes.

Everything is connected, and then there are the inputs.

With post net, you might recall, there were 34 inputs

Let's just say, for the sake of argument,

to be an individual input into this ML5 neural network.

and R, G, and B. So that would make 100 times three inputs,

So this is actually what I want to implement.

Take the idea of a two layer neural network

to perform classification, the same thing I've

done in previous videos, but, this time, use as the input

Can we get meaningful results from just doing that?

After we do that, I want to return back to here

and talk about why this is inadequate or not going

to say inadequate but how this can be improved on

And the output layer will still be there.

And I want to do a two dimensional convolutional

If you want to just skip to that next video,

But let's just get this working as a frame of reference.

I'm going to start with some prewritten code.

draws a rectangle in the canvas for each and every pixel.

How do you look at an image in JavaScript in P5

and address every single pixel individually?

If that's unfamiliar to you, I would refer

That's appearing over next to me right now.

If you go take a look at that and then come back here.

But really, this is just looking at every x and y position,

getting the R, G, B values, filling a rectangle,

So what I want to do next is think about,

how do I configure this ML5 neural network,

字幕列表影片播放

ml5.js：用像素作為輸入來訓練神經網絡。 (ml5.js: Train a Neural Network with Pixels as Input)

approach

scenario

opportunity

description