Name: 博士号を持たないTensorFlowとディープラーニング、その2（Google Cloud Next '17 (TensorFlow and Deep Learning without a PhD, Part 2 (Google Cloud Next '17))
Uploaded: 2021-01-14T06:50:37.000Z
Duration: 56 min 6 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：

MARTIN GORNER: So thank you for filling the house.

程度の副詞

So today, or yesterday, we built a neural network

And we went through dense neural networks

And today, I want to build with you another kind of network,

You remember, we started with this initial one layer neural

But it works for any input vector, of course.

And you remember, we said that the neurons

do weighted sums of all of their inputs, they add in bias,

and they feed that through some activation function.

It's just a function, value in, value out.

But usually, in neural networks, it's a non-linear function.

And we wrote this one layer neural network

using a matrix multiply, blah, blah, blah,

And you remember, we did this not for just one image,

And then x times w are all the weighted sums for our neurons.

We feed that through our activation function.

So in our case, since we were classifying handwritten digits,

which are the probabilities of these digits being a 0, a 1, 2,

you think, one layer of a neural network.

And then also, what I need you to remember

is that once we get our output from the neural network,

the way we train it is that we give it examples.

And then we say, no, no, no, no, no, that's not what we wanted.

And to do that, we have to encode this correct answer

So it's called-- it's a very basic type of encoding.

And basically here, if we have 10 categories,

specifying one answer category means encoding it as 10 0s,

but just one 1 somewhere in the middle, and the index of the 1

Means that the correct answer was a 6, OK?

So in this shape, it becomes possible to compute

a distance between what the network predicts

And that distance, we call that our error function.

Or sometimes, it's called the loss function.

That's what we use to guide our training.

So during training, we give it an example, produces an output.

We say, no, no, no, that's not what we wanted.

Compute the distance between what the network says

And from that distance, we derive the gradient.

And that modifies the weights and biases.

So now, let's look at this neural network.

It has a middle layer using the hyperbolic tangent

which is let's say the simplest possible function going

The hyperbolic tangent is the simplest possible function

And then, a second layer, which is a softmax

But the specificity is here that the output

of this intermediate green layer is actually

fed back in the next time step in the inputs.

So the real input into one cell of a recurrent neural network

is the input concatenated to the output of the inner layer

字幕リスト動画再生

博士号を持たないTensorFlowとディープラーニング、その2（Google Cloud Next '17 (TensorFlow and Deep Learning without a PhD, Part 2 (Google Cloud Next '17))

basically

character

sentence

previous