Deal of The Day! Hurry Up, Grab the Special Discount - Save 25% - Ends In 00:00:00 Coupon code: SAVE25

- Free Preparation Discussions

Google Professional Data Engineer Exam - Topic 3 Question 70 Discussion

Actual exam question for Google's Professional Data Engineer exam

Question #: 70
Topic #: 3

[All Professional Data Engineer Questions]

Which of the following are examples of hyperparameters? (Select 2 answers.)

ANumber of hidden layers

BNumber of nodes in each hidden layer

CBiases

DWeights

Show Suggested Answer

Suggested Answer: C

by Leslie at Sep 02, 2023, 10:48 PM

Limited Time Offer

25%

Off

Get Premium Professional Data Engineer Questions as Interactive Web-Based Practice Test or PDF

Contribute your Thoughts:

Submit Cancel

Pearlene

6 months ago

Yeah, A and B are the classic examples.

upvoted 0 times

...

Alton

7 months ago

Wait, are weights not hyperparameters? That’s surprising!

upvoted 0 times

...

Annmarie

7 months ago

Totally agree, A and B are the right choices!

upvoted 0 times

...

Wynell

7 months ago

I thought biases were hyperparameters too?

upvoted 0 times

...

Katy

7 months ago

A and B are definitely hyperparameters!

upvoted 0 times

...

Virgina

8 months ago

I'm a bit confused; I thought both the number of hidden layers and the number of nodes were hyperparameters, but I can't recall for sure.

upvoted 0 times

...

Eliz

8 months ago

I feel like biases and weights are more like parameters, not hyperparameters.

upvoted 0 times

...

Rikki

8 months ago

I remember practicing a question like this, and I think the number of nodes in each hidden layer is also a hyperparameter.

upvoted 0 times

...

Twana

8 months ago

I think the number of hidden layers is definitely a hyperparameter, but I'm not sure about the other one.

upvoted 0 times

...

Wei

8 months ago

Yep, I agree with Emily. Biases and weights are model parameters that get updated during training, not hyperparameters that are set beforehand.

upvoted 0 times

...

Brianne

8 months ago

I think the key is to focus on what can be adjusted before training versus what gets learned during training. The number of layers and nodes are set upfront, so those are hyperparameters.

upvoted 0 times

...

Mari

8 months ago

Wait, are biases and weights considered hyperparameters too? I'm a bit confused on that.

upvoted 0 times

...

Bambi

8 months ago

Okay, I've got this. The number of hidden layers and the number of nodes in each layer are definitely hyperparameters, since they're set before training the model.

upvoted 0 times

...

Gerri

8 months ago

Hmm, this looks like a tricky one. I'll need to think carefully about the difference between hyperparameters and model parameters.

upvoted 0 times

...

Miriam

8 months ago

Hmm, I'm a little unsure about this one. The options seem pretty similar, and I'm not totally clear on the difference between interfund reimbursement and interfund exchange. I'll have to think this through carefully.

upvoted 0 times

...

Glen

8 months ago

Hmm, I'm a bit unsure about this one. The options seem similar, and I want to make sure I understand the differences between them. Let me think this through carefully.

upvoted 0 times

...

Chanel

8 months ago

Isn't Service Discoverability more about how easily services can be found rather than restricting access? I feel a bit uncertain on this one.

upvoted 0 times

...

Emilio

1 year ago

I'm going with A and B. Gotta love those hidden layers and node counts! They're like the dials on a machine learning control panel.

upvoted 0 times

Domitila

11 months ago

It's important to understand the role of each hyperparameter in order to optimize the model.

upvoted 0 times

...

Dulce

11 months ago

I think biases and weights are more like parameters that get adjusted during training.

upvoted 0 times

...

Cassi

11 months ago

Yeah, those hidden layers and node counts can really impact the performance of the model.

upvoted 0 times

...

Oliva

1 year ago

I agree, A and B are definitely hyperparameters that can be tuned.

upvoted 0 times

...

...

Tabetha

1 year ago

Haha, this is a tricky one! I bet the exam creators just wanted to see if we can distinguish between the model's parameters and its hyperparameters. Time to brush up on my ML terminology!

upvoted 0 times

Jennifer

11 months ago

B) Number of nodes in each hidden layer

upvoted 0 times

...

Sharmaine

12 months ago

A) Number of hidden layers

upvoted 0 times

...

...

Lizbeth

1 year ago

Wait, I thought hyperparameters were external to the model, like the learning rate or the batch size. Isn't that what we're supposed to be looking for here?

upvoted 0 times

Anjelica

1 year ago

B) Number of nodes in each hidden layer

upvoted 0 times

...

Gerri

1 year ago

A) Number of hidden layers

upvoted 0 times

...

...

Georgeanna

1 year ago

I think biases and weights are also hyperparameters because they are set before training the model.

upvoted 0 times

...

Brent

1 year ago

I agree with Tawanna, hyperparameters include the number of hidden layers and nodes in each layer.

upvoted 0 times

...

Frederic

1 year ago

I'm pretty sure C and D are also hyperparameters. Biases and weights are part of the model's architecture and can be adjusted during the training process.

upvoted 0 times

Gilma

1 year ago

I agree, adjusting biases and weights can have a significant impact on the model's learning process.

upvoted 0 times

...

Salley

1 year ago

Yes, biases and weights are important hyperparameters that can affect the model's performance.

upvoted 0 times

...

Becky

1 year ago

I think you're right, biases and weights are also hyperparameters that can be tuned.

upvoted 0 times

...

Linn

1 year ago

D) Weights

upvoted 0 times

...

Dierdre

1 year ago

C) Biases

upvoted 0 times

...

Annmarie

1 year ago

B) Number of nodes in each hidden layer

upvoted 0 times

...

Eden

1 year ago

A) Number of hidden layers

upvoted 0 times

...

...

Tawanna

1 year ago

A) Number of hidden layers and B) Number of nodes in each hidden layer

upvoted 0 times

...

German

1 year ago

Hmm, I think A and B are the correct hyperparameters. The number of hidden layers and nodes in each layer are crucial hyperparameters that can be tuned to optimize the model's performance.

upvoted 0 times

...