| Question.66 A web-based company wants to improve its conversion rate on its landing page Using a large historical dataset of customer visits, the company has repeatedly trained a multi-class deep learning network algorithm on Amazon SageMaker However there is an overfitting problem training data shows 90% accuracy in predictions, while test data shows 70% accuracy only The company needs to boost the generalization of its model before deploying it into production to maximize conversions of visits to purchases Which action is recommended to provide the HIGHEST accuracy model for the company’s test and validation data? (A) Increase the randomization of training data in the mini-batches used in training. (B) Allocate a higher proportion of the overall data to the training dataset (C) Apply L1 or L2 regularization and dropouts to the training. (D) Reduce the number of layers and units (or neurons) from the deep learning network. |
66. Click here to View Answer
Correct Answer: C
Regularization and dropouts are techniques that can help reduce overfitting in deep learning models.
Overfitting occurs when the model learns too much from the training data and fails to generalize well to new data. Regularization adds a penalty term to the loss function that penalizes the model for having large or complex weights. This prevents the model from memorizing the noise or irrelevant features in the training data. L1 and L2 are two types of regularization that differ in how they calculate the penalty term. L1 regularization uses the absolute value of the weights, while L2 regularization uses the square of the weights.
Dropouts are another technique that randomly drops out some units or neurons from the network during training. This creates a thinner network that is less prone to overfitting. Dropouts also act as a form of ensemble learning, where multiple sub-models are combined to produce a better prediction. By applying regularization and dropouts to the training, the web-based company can improve the generalization and accuracy of its deep learning model on the test and validation data. References:
* Regularization: A video that explains the concept and benefits of regularization in deep learning.
* Dropout: A video that demonstrates how dropout works and why it helps reduce overfitting.
| Question.67 A machine learning (ML) specialist needs to extract embedding vectors from a text series. The goal is to provide a ready-to-ingest feature space for a data scientist to develop downstream ML predictive models. The text consists of curated sentences in English. Many sentences use similar words but in different contexts. There are questions and answers among the sentences, and the embedding space must differentiate between them. Which options can produce the required embedding vectors that capture word context and sequential QA information? (Choose two.) (A) Amazon SageMaker seq2seq algorithm (B) Amazon SageMaker BlazingText algorithm in Skip-gram mode (C) Amazon SageMaker Object2Vec algorithm (D) Amazon SageMaker BlazingText algorithm in continuous bag-of-words (CBOW) mode (E) Combination of the Amazon SageMaker BlazingText algorithm in Batch Skip-gram mode with a custom recurrent neural network (RNN) |
67. Click here to View Answer
Correct Answer: B,E
* To capture word context and sequential QA information, the embedding vectors need to consider both the order and the meaning of the words in the text.
* Option B, Amazon SageMaker BlazingText algorithm in Skip-gram mode, is a valid option because it can learn word embeddings that capture the semantic similarity and syntactic relations between words based on their co-occurrence in a window of words. Skip-gram mode can also handle rare words better than continuous bag-of-words (CBOW) mode1.
* Option E, combination of the Amazon SageMaker BlazingText algorithm in Batch Skip-gram mode with a custom recurrent neural network (RNN), is another valid option because it can leverage the advantages of Skip-gram mode and also use an RNN to model the sequential nature of the text. An RNN can capture the temporal dependencies and long-term dependencies between words, which are important for QA tasks2.
* Option A, Amazon SageMaker seq2seq algorithm, is not a valid option because it is designed for sequence-to-sequence tasks such as machine translation, summarization, or chatbots. It does not produce embedding vectors for text series, but rather generates an output sequence given an input sequence3.
* Option C, Amazon SageMaker Object2Vec algorithm, is not a valid option because it is designed for learning embeddings for pairs of objects, such as text-image, text-text, or image-image. It does not produce embedding vectors for text series, but rather learns a similarity function between pairs of objects4.
* Option D, Amazon SageMaker BlazingText algorithm in continuous bag-of-words (CBOW) mode, is not a valid option because it does not capture word context as well as Skip-gram mode. CBOW mode predicts a word given its surrounding words, while Skip-gram mode predicts the surrounding words given a word. CBOW mode is faster and more suitable for frequent words, but Skip-gram mode can learn more meaningful embeddings for rare words1.
1: Amazon SageMaker BlazingText
2: Recurrent Neural Networks (RNNs)
3: Amazon SageMaker Seq2Seq
4: Amazon SageMaker Object2Vec
| Question.68 A Machine Learning Specialist is training a model to identify the make and model of vehicles in images The Specialist wants to use transfer learning and an existing model trained on images of general objects The Specialist collated a large custom dataset of pictures containing different vehicle makes and models. What should the Specialist do to initialize the model to re-train it with the custom data? (A) Initialize the model with random weights in all layers including the last fully connected layer (B) Initialize the model with pre-trained weights in all layers and replace the last fully connected layer. (C) Initialize the model with random weights in all layers and replace the last fully connected layer (D) Initialize the model with pre-trained weights in all layers including the last fully connected layer |
68. Click here to View Answer
Correct Answer: B
Transfer learning is a technique that allows us to use a model trained for a certain task as a starting point for a machine learning model for a different task. For image classification, a common practice is to use a pre- trained model that was trained on a large and general dataset, such as ImageNet, and then customize it for the specific task. One way to customize the model is to replace the last fully connected layer, which is responsible for the final classification, with a new layer that has the same number of units as the number of classes in the new task. This way, the model can leverage the features learned by the previous layers, which are generic and useful for many image recognition tasks, and learn to map them to the new classes. The new layer can be initialized with random weights, and the rest of the model can be initialized with the pre-trained weights. This method is also known as feature extraction, as it extracts meaningful features from the pre-trained model and uses them for the new task. References:
* Transfer learning and fine-tuning
* Deep transfer learning for image classification: a survey
| Question.69 A Machine Learning Specialist is building a prediction model for a large number of features using linear models, such as linear regression and logistic regression During exploratory data analysis the Specialist observes that many features are highly correlated with each other This may make the model unstable What should be done to reduce the impact of having such a large number of features? (A) Perform one-hot encoding on highly correlated features (B) Use matrix multiplication on highly correlated features. (C) Create a new feature space using principal component analysis (PCA) (D) Apply the Pearson correlation coefficient |
69. Click here to View Answer
Correct Answer: C
Principal component analysis (PCA) is an unsupervised machine learning algorithm that attempts to reduce the dimensionality (number of features) within a dataset while still retaining as much information as possible.
This is done by finding a new set of features called components, which are composites of the original features that are uncorrelated with one another. They are also constrained so that the first component accounts for the largest possible variability in the data, the second component the second most variability, and so on. By using PCA, the impact of having a large number of features that are highly correlated with each other can be reduced, as the new feature space will have fewer dimensions and less redundancy. This can make the linear models more stable and less prone to overfitting. References:
* Principal Component Analysis (PCA) Algorithm – Amazon SageMaker
* Perform a large-scale principal component analysis faster using Amazon SageMaker | AWS Machine Learning Blog
* Machine Learning- Prinicipal Component Analysis | i2tutorials
| Question.70 A data science team is working with a tabular dataset that the team stores in Amazon S3. The team wants to experiment with different feature transformations such as categorical feature encoding. Then the team wants to visualize the resulting distribution of the dataset. After the team finds an appropriate set of feature transformations, the team wants to automate the workflow for feature transformations. Which solution will meet these requirements with the MOST operational efficiency? (A) Use Amazon SageMaker Data Wrangler preconfigured transformations to explore feature transformations. Use SageMaker Data Wrangler templates for visualization. Export the feature processing workflow to a SageMaker pipeline for automation. (B) Use an Amazon SageMaker notebook instance to experiment with different feature transformations. Save the transformations to Amazon S3. Use Amazon QuickSight for visualization. Package the feature processing steps into an AWS Lambda function for automation. (C) Use AWS Glue Studio with custom code to experiment with different feature transformations. Save the transformations to Amazon S3. Use Amazon QuickSight for visualization. Package the feature processing steps into an AWS Lambda function for automation. (D) Use Amazon SageMaker Data Wrangler preconfigured transformations to experiment with different feature transformations. Save the transformations to Amazon S3. Use Amazon QuickSight for visualzation. Package each feature transformation step into a separate AWS Lambda function. Use AWS Step Functions for workflow automation. |
70. Click here to View Answer
Correct Answer: A
The solution A will meet the requirements with the most operational efficiency because it uses Amazon SageMaker Data Wrangler, which is a service that simplifies the process of data preparation and feature engineering for machine learning. The solution A involves the following steps:
* Use Amazon SageMaker Data Wrangler preconfigured transformations to explore feature transformations. Amazon SageMaker Data Wrangler provides a visual interface that allows data scientists to apply various transformations to their tabular data, such as encoding categorical features, scaling numerical features, imputing missing values, and more. Amazon SageMaker Data Wrangler also supports custom transformations using Python code or SQL queries1.
* Use SageMaker Data Wrangler templates for visualization. Amazon SageMaker Data Wrangler also provides a set of templates that can generate visualizations of the data, such as histograms, scatter plots, box plots, and more. These visualizations can help data scientists to understand the distribution and characteristics of the data, and to compare the effects of different feature transformations1.
* Export the feature processing workflow to a SageMaker pipeline for automation. Amazon SageMaker Data Wrangler can export the feature processing workflow as a SageMaker pipeline, which is a service that orchestrates and automates machine learning workflows. A SageMaker pipeline can run the feature processing steps as a preprocessing step, and then feed the output to a training step or an inference step. This can reduce the operational overhead of managing the feature processing workflow and ensure its consistency and reproducibility2.
The other options are not suitable because:
* Option B: Using an Amazon SageMaker notebook instance to experiment with different feature transformations, saving the transformations to Amazon S3, using Amazon QuickSight for visualization, and packaging the feature processing steps into an AWS Lambda function for automation will incur more operational overhead than using Amazon SageMaker Data Wrangler. The data scientist will have to write the code for the feature transformations, the data storage, the data visualization, and the Lambda function. Moreover, AWS Lambda has limitations on the execution time, memory size, and package size, which may not be sufficient for complex feature processing tasks3.
* Option C: Using AWS Glue Studio with custom code to experiment with different feature transformations, saving the transformations to Amazon S3, using Amazon QuickSight for visualization, and packaging the feature processing steps into an AWS Lambda function for automation will incur more operational overhead than using Amazon SageMaker Data Wrangler. AWS Glue Studio is a visual interface that allows data engineers to create and run extract, transform, and load (ETL) jobs on AWS Glue. However, AWS Glue Studio does not provide preconfigured transformations or templates for feature engineering or data visualization. The data scientist will have to write custom code for these tasks, as well as for the Lambda function. Moreover, AWS Glue Studio is not integrated with SageMaker pipelines, and it may not be optimized for machine learning workflows4.
* Option D: Using Amazon SageMaker Data Wrangler preconfigured transformations to experiment with different feature transformations, saving the transformations to Amazon S3, using Amazon QuickSight for visualization, packaging each feature transformation step into a separate AWS Lambda function, and using AWS Step Functions for workflow automation will incur more operational overhead than using Amazon SageMaker Data Wrangler. The data scientist will have to create and manage multiple AWS Lambda functions and AWS Step Functions, which can increase the complexity and cost of the solution. Moreover, AWS Lambda and AWS Step Functions may not be compatible with SageMaker pipelines, and they may not be optimized for machine learning workflows5.
1: Amazon SageMaker Data Wrangler
2: Amazon SageMaker Pipelines
3: AWS Lambda
4: AWS Glue Studio
5: AWS Step Functions