Scribd
Upload
35 views

2nd Course

Uploaded by

cipuqoqi
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
35 views

2nd Course

Uploaded by

cipuqoqi
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 4

1. **Which of the following statements is true of TensorFlow?

**

**Answer:** TensorFlow is a scalable and multi-platform programming interface


for implementing and running machine learning algorithms, including convenience
wrappers for deep learning.

2. **How does TensorFlow represent numeric computations?**

**Answer:** Using a Directed Acyclic Graph (or DAG)

3. **Which are useful components when building custom Neural Network


models?**

**Answer:** All of the options are correct.

4. **Which API is used to build performant, complex input pipelines from simple,
re-usable pieces that will feed your model's training or evaluation loops?**

**Answer:** tf.data.Dataset

5. **What operations can be performed on tensors?**

**Answer:** They can be both reshaped and sliced

6. **Which of the following is true when we compute a loss gradient?**

**Answer:** All options are correct.

1. **What are distinct ways to create a dataset?**

**Answer:** A data source constructs a Dataset from data stored in memory or in one
or more files and a data transformation constructs a dataset from one or more
tf.data.Dataset objects.

2. **Which is true regarding feature columns?**


**Answer:** Feature columns describe how the model should use raw input data from
your features dictionary.

3. **Which of the following is true about embedding?**

**Answer:** All options are correct.

4. **What is the use of tf.keras.layers.TextVectorization?**

**Answer:** It turns raw strings into an encoded representation that can be read by an
Embedding layer or Dense layer.

5. **Which of the following is not a part of Categorical features preprocessing?**

**Answer:** tf.keras.layers.Discretization

6. **Which of the following layers is not non-trainable?**

**Answer:** Normalization

7. **When should you avoid using the Keras function adapt()?**

**Answer:** When working with lookup layers with very large vocabularies

8. **Which of the following is a part of Keras preprocessing layers?**

**Answer:** All of the options are correct.

1. **Non-linearity helps in training your model at a much faster rate and with more
accuracy without the loss of your important information?**

**Answer:** True

2. **During the training process, each additional layer in your network can successively
reduce signal vs. noise. How can we fix this?**
**Answer:** Use non-saturating, nonlinear activation functions such as ReLUs.

3. **How does Adam (optimization algorithm) help in compiling the Keras model?**

**Answer:** Both by updating network weights iteratively based on training data and
by diagonal rescaling of the gradients.

4. **The predict function in the tf.keras API returns what?**

**Answer:** Numpy array(s) of predictions

5. **What is the significance of the Fit method while training a Keras model?**

**Answer:** Defines the number of epochs

6. **Select the correct statement regarding the Keras Functional API.**

**Answer:** Unlike the Keras Sequential API, we have to provide the shape of the input
to the model.

7. **The Keras Functional API can be characterized by having:**

**Answer:** Multiple inputs and outputs and models with shared layers.

8. **How does regularization help build generalizable models?**

**Answer:** By adding dropout layers to our neural networks

9. **The L2 regularization provides which of the following?**

**Answer:** It adds a sum of the squared parameter weights term to the loss function.

1. **Fill in the blanks. When sending training jobs to Vertex AI, it is common to split most
of the logic into a _________ and a ___________ file.**

**Answer:** task.py, model.py


2. **Which file is the entry point to your code that Vertex AI will start and contains
details such as “how to parse command-line arguments and where to write model
outputs?"**

**Answer:** task.py

3. **When you package up a TensorFlow model as a Python Package, what statement


should every Python module contain in every folder?**

**Answer:** an init_.py

4. **To make your code compatible with Vertex AI, there are three basic steps that must
be completed in a specific order. Choose the answer that best describes those steps.**

**Answer:** First, upload data to Google Cloud Storage. Next, move code into a trainer
Python package. Then submit your training job with gcloud to train on Vertex AI.

5. **Fill in the blanks. You can use either pre-built containers or custom containers to
run training jobs. Both containers require you specify settings that Vertex AI needs to run
your training code, including __________, ____________, and ________.**

**Answer:** Region, display-name, worker-pool-spec

You might also like