Module 2

Question 1

What are the four major challenges, data engineers and data scientists are facing? (Known as 4Vs)

Answer 1

variety, volume, velocity, and veracity.

Question 2

True or False: “We can create and execute machine learning models on your structured datasets in BigQuery”

Answer 2

True

Question 3

What are the two services that BigQuery provides in one?

Answer 3

A fully managed storage facility to load and store datasets, and also a fast SQL-based analytical engine.

Question 4

….. is a large store, containing terabytes and petabytes of data gathered from a wide range of sources within an organization, that’s used to guide management decisions.

Answer 4

BigQuery

Question 5

Can we perform hyperparameter tuning in BigQuery?

Answer 5

Yes, With BigQuery ML, you can either manually control the hyperparameters or hand it to BigQuery starting with a default hyperparameter setting and then automatic tuning.

Question 6

What is One-hot encoding?

Answer 6

One-hot encoding is a method of converting categorical data to numeric data to prepare it for model training.

Question 7

True or False: “BigQuery ML doesn’t automatically perform one-hot encoding of categorical values”

Answer 7

False

Question 8

What is the phase 1 in a machine learning project?

Answer 8

In phase 1, you extract, transform, and load data into BigQuery, if it isn’t there already.

Question 9

What does ML.PREDICT command do in BigQuery?

Answer 9

you can use the ML.PREDICT command on a trained model, and pass through the dataset you want to make the prediction on.

Question 10

While the model is running, and even after it’s complete, you can view training progress with ….

Answer 10

ML.TRAINING_INFO

Question 11

What are the four options Google Cloud offers for building machine learning models?

Answer 11

BigQueryML, AutoML, Pre-built APIs, Custom training

Question 12

What is the difference between loss and cost function?

Question 13

What are the three main stage of ML workflow?

Answer 13

Data Preparing, Model Development, Model Serving

Question 14

…. is a set of tools and frameworks to help understand and interpret predictions made by machine learning models.

Answer 14

Explainable AI

Question 15

A farm uses the machine learning technology of Google to detect defective apples in their crop, like those with irregular sizes or scratches. The goal is to identify only the apples that are actually bad so that no good apples are wasted. Which metric should the model focus on?

Answer 15

Precision

Question 16

A hospital uses the machine learning technology of Google to help pre-diagnose cancer by feeding historical patient medical data to the model. The goal is to identify as many potential cases as possible. Which metric should the model focus on?

Answer 16

Recall

Question 17

We can use … to quickly prototype and customize generative AI models with no or low code.

Answer 17

Generative AI Studio

Question 18

What is Zero-shot prompting?

Answer 18

Zero-shot prompting is a method where the LLM is given no additional data on the specific task that it is being asked to perform.

Question 19

What are the 3 methods you can use to shape the GenAI model’s response in a way that you desire.

Answer 19

Zero-shot, one-shot and few-shot prompting

Question 20

What is temperature in GenAI?

Answer 20

Temperature is a number used to tune the degree of randomness. Low temperature: Means to narrow the range of possible words to those that have high possibilities and are more typical.

Question 21

Low or high temperature for scenarios like questions-and-answers and summarization?

Answer 21

Low temperature

Question 22

What is top-K and top-P in GenAI?

Answer 22

op K lets the model randomly return a word from the top K number of words in terms of possibility. Top P allows the model to return a random word from the smallest subset with the sum of the likelihoods that exceeds or equals to P. For instance, P of 0.75 means you sample from a set of words that have a cumulative probability greater than 0.75.

Question 23

Which of the following is a type of prompt that allows a large language model to perform a task with only a small number of examples?

Unsupervised prompt

One-shot prompt

Zero-shot prompt

Few-shot prompt

Answer 23

Few-shot prompt

Question 24

Which of the following is the best way to generate more creative or unexpected content by adjusting the model parameters in Generative AI Studio?

Set the temperature to a low value.

Set the top P to 25%.

Set the top K to 1.

Set the temperature to a high value.

Answer 24

Set the temperature to a high value.