AIF-C01 Fundamentals of AI and ML — 25 Questions

Question 1

An ML team is deploying a real-time inference endpoint for a computer vision model using Amazon SageMaker. The model requires GPU acceleration for low latency. Which instance type should the team choose to minimize cost while meeting the GPU requirement?

Choose an answer to begin — your selection is scored in the full session.

Accepted Answer

ml.g5.xlarge. (ml.g5.xlarge) is correct because it provides a GPU (NVIDIA A10G Tensor Core GPU) necessary for low-latency GPU acceleration in computer vision inference, while being the most cost-effective GPU instance among the options. The ml.g5.xlarge offers sufficient GPU compute for real-time inference at a lower hourly cost compared to ml.p3.2xlarge, making it the optimal choice for minimizing cost while meeting the GPU requirement.

Answer

ml.c5.xlarge

Answer

ml.p3.2xlarge

Answer

ml.p4d.24xlarge

Question 2

A company is training a deep learning model on Amazon SageMaker using a custom Docker container. The training job fails with the error 'CannotStartContainerError: API error (500): failed to create shim task'. The team verifies that the container image is compatible with the selected instance type. What is the most likely cause of this error?

Accepted Answer

The instance type does not have enough memory for the container. The error 'CannotStartContainerError: API error (500): failed to create shim task' typically occurs when the Docker container cannot be initialized due to resource constraints, most commonly insufficient memory on the selected instance type. Even if the container image is compatible with the instance, the container's memory request may exceed the available memory, causing the container runtime (containerd) to fail when creating the shim task. This is a known issue in SageMaker when the training job's resource requirements are not aligned with the instance's capacity.

Answer

The training data is stored in the wrong S3 bucket

Answer

The container image does not have the correct entry point

Answer

The GPU drivers are outdated

Question 3

A machine learning engineer is using Amazon SageMaker to train a model and wants to automatically stop the training job if the loss does not improve for 10 consecutive epochs. Which SageMaker feature should be used?

Accepted Answer

SageMaker built-in algorithms with early stopping. Amazon SageMaker built-in algorithms support early stopping, which allows you to automatically terminate a training job when a specified metric, such as loss, stops improving for a defined number of consecutive epochs. This feature is configured directly in the algorithm's hyperparameters (e.g., `early_stopping_patience` for the XGBoost algorithm) and helps save compute time and cost by preventing overfitting.

Answer

SageMaker Training Compiler

Answer

SageMaker Debugger

Answer

SageMaker Experiments

Question 4

Refer to the exhibit. A data scientist attaches the above IAM policy to a SageMaker notebook instance role. The notebook is in the same AWS account as the S3 bucket. When trying to read a file from 's3://my-bucket/training/data.csv', the data scientist gets an Access Denied error. What is the most likely cause?

Accepted Answer

The S3 bucket is in a different Region. The Access Denied error is most likely due to the S3 bucket being in a different Region. While IAM policies are global, bucket policies can include conditions that restrict access based on the request's Region. If the bucket policy denies requests from the Region where the SageMaker notebook is running, the read operation fails. The other options are incorrect: file name spaces cause a different error (NoSuchKey), s3:ListBucket is not required for direct object reads with GetObject, and allowing s3:PutObject does not cause Access Denied for reads.

Answer

The file name contains spaces

Answer

The policy does not grant 's3:ListBucket' permission

Answer

The policy allows 's3:PutObject' which is not needed

Question 5

Refer to the exhibit. A data scientist is training a neural network model on SageMaker. The training log shows the loss values per epoch. Which issue is most likely occurring?

Accepted Answer

The model is overfitting. The training log shows loss values decreasing on the training set but increasing or plateauing on the validation set, which is a classic sign of overfitting. Overfitting occurs when the model learns noise and specific patterns in the training data too well, failing to generalize to unseen data. In SageMaker, monitoring both training and validation loss curves is critical to detect this issue early.

Answer

The number of epochs is insufficient

Answer

The dataset is too small

Answer

The learning rate is too low

Question 6

A financial services company uses a machine learning model to approve loan applications. The model is a gradient boosting classifier trained on historical loan data. Recently, the company noticed that the model's approval rate for applicants from a certain demographic group is significantly lower than for other groups, even though the model's overall accuracy remains high. The data science team has been asked to address this potential bias while minimizing the impact on overall model performance. The team has access to the training data and the trained model. They have limited time and budget. Which course of action should the team take first?

Accepted Answer

Analyze the training data for bias and retrain the model using bias mitigation techniques such as reweighting.. The first step should be to analyze the training data for bias, as biases often originate from historical imbalances or labeling issues. Once bias is identified, techniques like reweighting can be applied during retraining to mitigate bias with minimal impact on overall performance. Option A (removing the sensitive attribute) is insufficient because other features may correlate with the sensitive attribute, and the model can still learn biased patterns. Option B (collecting more data from the under-represented group) is resource-intensive and may not be feasible within limited time and budget; also, it does not address bias in the existing data. Option D (adjusting threshold after deployment) is a post-hoc fix that can lead to inconsistent decisions and may not address the root cause; it is better to address bias during training.

Answer

Remove the sensitive attribute from the training data and retrain the model.

Answer

Collect more data from the under-represented demographic group and retrain the model.

Answer

Adjust the model's decision threshold for the affected group after deployment.

Question 7

A retail company uses a machine learning model to forecast daily product demand. The model is a time series model that uses historical sales data. The model has been performing well, but recently the forecasts have been consistently too low, leading to stockouts. The data scientist notices that the model was trained on data up to last year, and the company has since launched a successful marketing campaign that increased sales by 20%. The data scientist needs to update the model to reflect the new sales patterns. Which approach should the data scientist take?

Accepted Answer

Retrain the model on the most recent data that includes the sales from the marketing campaign.. Retraining the model on the most recent data that includes the sales from the marketing campaign allows the model to learn the new underlying pattern in the time series. Since the model is a time series model, it relies on historical patterns to make forecasts; retraining on data that captures the 20% sales lift ensures the model adapts to the new demand level, reducing the persistent underforecasting.

Answer

Add a feature for the marketing campaign and continue using the old model.

Answer

Switch to a different model type, such as ARIMA, without retraining.

Answer

Multiply the model's predictions by 1.2 to account for the marketing campaign.

Question 8

A data scientist is preparing data for a machine learning model. What is the purpose of splitting the data into training, validation, and test sets?

Accepted Answer

To evaluate model generalization. The test set is held out entirely from the training process and is used only once at the end to evaluate the model's performance on unseen data. This provides an unbiased estimate of how well the model generalizes to new, real-world data, which is the ultimate goal of supervised learning.

Answer

To tune hyperparameters

Answer

To balance class distributions

Answer

To prevent overfitting during training

Question 9

A data scientist is working with a dataset that contains both numerical and categorical features. Which algorithm is commonly used for regression tasks in AWS SageMaker?

Accepted Answer

Linear Learner. Linear Learner (option B) is the correct choice because it is a supervised learning algorithm in AWS SageMaker specifically designed for both regression and classification tasks. It can handle datasets with mixed numerical and categorical features (after appropriate encoding) and provides built-in mechanisms for training linear models, including automatic model tuning and distributed training. Note that option D is a duplicate of option B and is not considered the correct answer in this context.

Answer

K-Means

Answer

BlazingText

Answer

Linear Learner

Question 10

A team has built a regression model to predict house prices. The RMSE is 50,000 on the test set. Which action is most appropriate to improve model performance?

Accepted Answer

Add more relevant features. Adding more relevant features can provide the model with additional predictive signals, potentially reducing bias and lowering RMSE if the new features have genuine correlation with house prices. Since RMSE is already 50,000, the model may be underfitting due to insufficient input variables, and enriching the feature set is a direct way to capture more variance in the target variable.

Answer

Remove outliers from training data

Answer

Apply feature scaling

Answer

Use a different evaluation metric

Question 11

A data scientist needs to preprocess categorical data with high cardinality (e.g., zip code with 50,000 unique values). Which technique is most appropriate?

Accepted Answer

Target encoding. Target encoding is the most appropriate technique for high-cardinality categorical features like zip codes because it replaces each category with the mean of the target variable for that category, effectively compressing 50,000 unique values into a single numeric feature while retaining predictive signal. This avoids the dimensionality explosion of one-hot encoding and the arbitrary ordering of label or ordinal encoding, which can mislead models.

Answer

Label encoding

Answer

Ordinal encoding

Answer

One-hot encoding

Question 12

Refer to the exhibit. A user tries to create a training job that reads data from a bucket named 'my-bucket'. The job fails with an access denied error. What is the most likely cause?

Accepted Answer

The s3:GetObject permission is missing the bucket ARN for listing objects. The error 'access denied' when reading data from S3 typically indicates that the IAM role used by SageMaker lacks the necessary permissions. Specifically, the s3:ListBucket permission is required to list objects in the bucket, and the s3:GetObject permission is required to retrieve them. Without the s3:ListBucket permission (or with an incomplete resource ARN), the job cannot enumerate objects, leading to the access denied error. Option C correctly identifies the missing bucket ARN for listing objects, which corresponds to the missing s3:ListBucket action.

Answer

The s3:GetObject action is restricted to a specific bucket but the bucket ARN is incorrect

Answer

The sagemaker:CreateTrainingJob action is not allowed for the specific instance type

Answer

The IAM role does not have permission to write to the bucket

Question 13

A manufacturing company is deploying IoT sensors to monitor equipment performance. The sensors generate continuous unlabeled time-series data with thousands of dimensions. The goal is to detect anomalies indicating potential failures in real time. The data science team has experience with unsupervised learning and wants to use a SageMaker built-in algorithm that can handle high-dimensional data and identify outliers. They also need to reduce the number of dimensions to improve training speed without losing important information. Which approach should they take?

Accepted Answer

Use Amazon SageMaker Random Cut Forest algorithm. Amazon SageMaker Random Cut Forest (RCF) is a built-in unsupervised algorithm specifically designed for anomaly detection on high-dimensional time-series data. RCF does not explicitly reduce dimensions via techniques like PCA; instead, it randomly samples features at each split in its ensemble of random trees. This random subsampling effectively reduces the number of dimensions considered per tree, allowing the algorithm to handle thousands of dimensions without explicit reduction while preserving anomaly detection accuracy. Since the team needs to detect anomalies and the data is unlabeled, RCF is the most appropriate choice among the options. Note that no SageMaker built-in algorithm performs explicit dimensionality reduction; RCF's random feature sampling meets the requirement of improving training speed by reducing the effective feature space per tree.

Answer

Use Amazon SageMaker Linear Learner algorithm

Answer

Use Amazon SageMaker Image Classification algorithm

Answer

Use Amazon SageMaker Object Detection algorithm

Question 14

A data science team needs to choose a machine learning approach for a project that requires predicting customer churn based on historical data. The team has a labeled dataset with 10,000 records and needs to interpret the model's decisions to provide business insights. Which machine learning technique should the team prioritize?

Accepted Answer

Random forest.. Random forest is the best choice because it handles the classification task of predicting churn (a binary outcome) from a labeled dataset, provides feature importance scores for interpretability, and works well with 10,000 records without overfitting due to its ensemble of decision trees. Its built-in ability to rank input features directly supports the team's need to derive business insights from model decisions.

Answer

K-means clustering.

Answer

Linear regression.

Answer

Deep neural network with multiple hidden layers.

Question 15

Refer to the exhibit. A data scientist trained an XGBoost model using Amazon SageMaker. Which TWO actions should the data scientist take to improve the model's performance based on the exhibited training job metrics and resource configuration?

Accepted Answer

Decrease the learning rate and increase the number of training rounds.. Decreasing the learning rate and increasing the number of training rounds allows the XGBoost model to take smaller, more precise steps toward the loss minimum, reducing the risk of overshooting and improving convergence. Increasing the maximum number of leaf nodes increases the model's capacity to capture complex patterns in the data, which can reduce underfitting and improve performance if the current model is too simple.

Answer

Reduce the VolumeSizeInGB to save costs.

Answer

Use a distributed training strategy by increasing InstanceCount to 4.

Answer

Switch to a more powerful instance type to reduce training time.

Question 16

A company is building a chatbot to answer customer queries using Amazon Lex. The development team has created a large dataset of customer interactions and intends to use Amazon SageMaker to train a custom machine learning model for natural language understanding (NLU). The team wants to integrate the trained model with Amazon Lex to handle intents and slots. The team has limited experience with SageMaker and wants to minimize operational overhead. Which solution should the team use?

Accepted Answer

Use SageMaker Autopilot to automatically build and train the best model, then deploy to a SageMaker endpoint and use Lambda to invoke it for Lex integration.. SageMaker Autopilot automates model building, tuning, and deployment, reducing manual effort and expertise required. Option A is not supported as Amazon Lex does not directly invoke custom Docker containers; integration is typically via Lambda. Option B uses SageMaker BlazingText, which requires manual algorithm selection and tuning, not minimizing operational overhead. Option C uses Amazon Comprehend, which provides general-purpose NLP but cannot train custom NLU models for Lex intents and slots.

Answer

Encapsulate the custom model in a Docker container, push it to Amazon ECR, and create a custom machine learning resource in Amazon Lex to invoke the container directly.

Answer

Train a custom model in SageMaker using a built-in algorithm like BlazingText, then deploy it to a SageMaker endpoint and integrate with Lex via a AWS Lambda function that calls the endpoint.

Answer

Use Amazon Comprehend to perform sentiment analysis and entity recognition, then map the results to Lex intents using Lambda.

Question 17

A data scientist wants to quickly build a supervised learning model for binary classification on a tabular dataset with 10,000 rows and 200 features. The dataset has some missing values and requires minimal code. Which AWS service should the data scientist use?

Accepted Answer

Amazon SageMaker Autopilot. Amazon SageMaker Autopilot is the correct choice because it automatically performs data preprocessing (including handling missing values), feature engineering, model selection, and hyperparameter tuning for supervised learning tasks like binary classification. It requires minimal code—users can simply point to a tabular dataset in Amazon S3 and specify the target column, and Autopilot will automatically train and evaluate multiple candidate models, making it ideal for quickly building a binary classifier on a 10,000-row, 200-feature dataset with missing values.

Answer

Amazon SageMaker Studio Lab

Answer

Amazon SageMaker Clarify

Answer

Amazon SageMaker JumpStart

Question 18

A company needs to store large amounts of unstructured training data (images, videos) in a cost-effective manner while ensuring low-latency retrieval for training jobs running on Amazon SageMaker. Which storage solution should be used?

Accepted Answer

Amazon S3. Amazon S3 is the correct choice because it is designed for cost-effective, scalable storage of unstructured data (images, videos) and integrates natively with Amazon SageMaker for low-latency data retrieval during training jobs. S3 provides high throughput and can be accessed directly from SageMaker training instances without the need for file system mounting, making it ideal for large-scale ML workloads.

Answer

Amazon EFS

Answer

Amazon RDS

Answer

Amazon EBS

Question 19

An organization wants to detect anomalies in real-time streaming data from IoT devices. The data includes sensor readings, and the team plans to use a machine learning model. Which AWS service should be used to build and deploy the model with minimal operational overhead?

Accepted Answer

Amazon SageMaker. Amazon SageMaker is the correct choice because it provides a fully managed environment for building, training, and deploying machine learning models at scale. For real-time anomaly detection on streaming IoT data, SageMaker can host a trained model as a real-time endpoint that processes incoming sensor readings via Amazon Kinesis Data Streams or AWS Lambda, minimizing operational overhead by handling infrastructure, scaling, and monitoring automatically.

Answer

AWS Glue

Answer

Amazon QuickSight

Answer

Amazon Kinesis Data Analytics

Question 20

During a SageMaker training job, the data scientist observes that the loss is not decreasing after the initial few epochs. The model is a deep neural network with ReLU activations. Which hyperparameter adjustment is most likely to help?

Accepted Answer

Reduce the learning rate. When loss plateaus after a few epochs with ReLU activations, the model is likely stuck in a region where gradients are small (e.g., near a local minimum or plateau). Reducing the learning rate allows the optimizer to take smaller steps, which can help it navigate out of flat regions and continue decreasing the loss. This is a standard technique to improve convergence when training stalls.

Answer

Increase the number of epochs

Answer

Increase the learning rate

Answer

Decrease the batch size