Name: 量子ニューラルネットワークの層別学習 (TF Dev Summit '20) (Layer-wise learning for quantum neural networks (TF Dev Summit '20))
Uploaded: 2021-01-14T10:38:05.000Z
Duration: 5 min 11 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：

DAVID VON DOLLEN: Hello, my name is David Von Dollen.

And I'm here today to talk about layer wise learning

for Volkswagen Group of America working on a variety of topics,

including quantum computing and machine learning out

a little bit of an intuition about quantum neural networks.

of circuit, where we have a register of qubits

with which we load some data, whether it's

For our project we looked at classical data, specifically

And then you apply a series of unitary gates.

Now these can be random rotation gates, namely rotation y, x,

Finally, we apply a readout on one qubit.

And with this we calculate a gradient for our parameters

Now a known problem for quantum neural networks

is what's called the barren plateau problem.

is that as the depth of a quantum neural network grows,

the variance of the gradients in randomly initialized quantum

And so, given this problem, we developed this technique,

we address the vanishing gradient problem.

But we also looked at using this new library, TensorFlow

Quantum, to train and experimentally verify

is that it handles all of our training overhead.

And we can focus on research, rather than coding and getting

So looking at this vanishing gradient problem,

we may utilize larger gradients in shallow quantum neural

We can avoid configurations and random initialization,

which may lead to a barren plateau problem

And we can successively grow our quantum neural network layer

another layer, freezing, and then also training and freezing

So when we look at this layerwise learning,

we can think about this phase of sweeping

over the network, where we look at the first layer.

We train our second parameter, and we freeze and so on.

And we also see a performance gain in our test error.

So when we looked at doing binary classification

we noticed an advantage when using 10 epochs per layer

in doing layerwise learning over what we call complete depth

learning, where we train all of the layers at once.

So to talk a little bit about TensorFlow Quantum,

we can generate our quantum neural network layers really

easily by using sympy and cirq to construct our circuit.

And we can use the TensorFlow Keras loss functions

and optimizers to train the gradients for our parameters

This has been a really great collaboration

字幕リスト動画再生

量子ニューラルネットワークの層別学習 (TF Dev Summit '20) (Layer-wise learning for quantum neural networks (TF Dev Summit '20))

essentially

technique

advantage

specifically