AWS Machine Learning Specialty Certification Exam Syllabus

MLS-C01 Dumps Questions, MLS-C01 PDF, Machine Learning Specialty Exam Questions PDF, AWS MLS-C01 Dumps Free, Machine Learning Specialty Official Cert Guide PDFThe AWS MLS-C01 exam preparation guide is designed to provide candidates with necessary information about the Machine Learning Specialty exam. It includes exam summary, sample questions, practice test, objectives and ways to interpret the exam objectives to enable candidates to assess the types of questions-answers that may be asked during the AWS Certified Machine Learning - Specialty exam.

It is recommended for all the candidates to refer the MLS-C01 objectives and sample questions provided in this preparation guide. The AWS Machine Learning Specialty certification is mainly targeted to the candidates who want to build their career in Specialty domain and demonstrate their expertise. We suggest you to use practice exam listed in this cert guide to get used to with exam environment and identify the knowledge areas where you need more work prior to taking the actual AWS Certified Machine Learning - Specialty exam.

AWS MLS-C01 Exam Summary:

Exam Name AWS Certified Machine Learning - Specialty (Machine Learning Specialty)
Exam Code MLS-C01
Exam Price $300 USD
Duration 180 minutes
Number of Questions 65
Passing Score 750 / 1000
Recommended Training / Books Practical Data Science with Amazon SageMaker
Schedule Exam AWS Certification
Sample Questions AWS MLS-C01 Sample Questions
Recommended Practice AWS Certified Machine Learning - Specialty Practice Test

AWS Machine Learning Specialty Syllabus:

Section Objectives

Data Engineering - 20%

Create data repositories for ML. - Identify data sources (for example, content and location, primary sources such as user data).
- Determine storage mediums (for example, databases, Amazon S3, Amazon Elastic File System [Amazon EFS], Amazon Elastic Block Store [Amazon EBS]).
Identify and implement a data ingestion solution. - Identify data job styles and job types (for example, batch load, streaming).
- Orchestrate data ingestion pipelines (batch-based ML workloads and streaming-based ML workloads).
  • Amazon Kinesis
  • Amazon Data Firehose
  • Amazon EMR
  • AWS Glue
  • Amazon Managed Service for Apache Flink

- Schedule jobs.

Identify and implement a data transformation solution. - Transform data in transit (ETL, AWS Glue, Amazon EMR, AWS Batch).
- Handle ML-specific data by using MapReduce (for example, Apache Hadoop, Apache Spark, Apache Hive).

Exploratory Data Analysis - 24%

Sanitize and prepare data for modeling.

- Identify and handle missing data, corrupt data, and stop words.
- Format, normalize, augment, and scale data.
- Determine whether there is sufficient labeled data.

  • Identify mitigation strategies.
  • Use data labelling tools (for example, Amazon Mechanical Turk).
Perform feature engineering. - Identify and extract features from datasets, including from data sources such as text, speech, image, public datasets.
- Analyze and evaluate feature engineering concepts (for example, binning, tokenization, outliers, synthetic features, one-hot encoding, reducing dimensionality of data).
Analyze and visualize data for ML. - Create graphs (for example, scatter plots, time series, histograms, box plots).
- Interpret descriptive statistics (for example, correlation, summary statistics, p-value).
- Perform cluster analysis (for example, hierarchical, diagnosis, elbow plot, cluster size).

Modeling - 36%

Frame business problems as ML problems. - Determine when to use and when not to use ML.
- Know the difference between supervised and unsupervised learning.
- Select from among classification, regression, forecasting, clustering, and recommendation and foundation models.
Select the appropriate model(s) for a given ML problem. - XGBoost, logistic regression, k-means, linear regression, decision trees, random forests, RNN, CNN, ensemble, transfer learning and large language models (LLMs)
- Express the intuition behind models.
Train ML models. - Split data between training and validation (for example, cross validation).
- Understand optimization techniques for ML training (for example, gradient descent, loss functions, convergence).
- Choose appropriate compute resources (for example GPU or CPU, distributed or non-distributed).
  • Choose appropriate compute platforms (Spark or non-Spark).

- Update and retrain models.

  • Batch or real-time/online
Perform hyperparameter optimization. - Perform regularization.
  • Dropout
  • L1/L2

- Perform cross-validation.
- Initialize models.
- Understand neural network architecture (layers and nodes), learning rate, and activation functions.
- Understand tree-based models (number of trees, number of levels).
- Understand linear models (learning rate).

Evaluate ML models. - Avoid overfitting or underfitting.
  • Detect and handle bias and variance.

- Evaluate metrics (for example, area under curve [AUC]-receiver operating characteristics [ROC], accuracy, precision, recall, Root Mean Square Error [RMSE], F1 score).
- Interpret confusion matrices.
- Perform offline and online model evaluation (A/B testing).
- Compare models by using metrics (for example, time to train a model, quality of model, engineering costs).
- Perform cross-validation.

Machine Learning Implementation and Operations - 20%

Build ML solutions for performance, availability, scalability, resiliency, and fault tolerance. - Log and monitor AWS environments.
  • AWS CloudTrail and Amazon CloudWatch
  • Build error monitoring solutions.

- Deploy to multiple AWS Regions and multiple Availability Zones.
- Create AMIs and golden images.
- Create Docker containers.
- Deploy Auto Scaling groups.
- Rightsize resources (for example, instances, Provisioned IOPS, volumes).
- Perform load balancing.
- Follow AWS best practices.

Recommend and implement the appropriate ML services and features for a given problem. - ML on AWS (application services), for example:
  • Amazon Polly
  • Amazon Lex
  • Amazon Transcribe

- Understand AWS service quotas.
- Determine when to build custom models and when to use Amazon SageMaker built-in algorithms.
- Understand AWS infrastructure (for example, instance types) and cost considerations.

  • Use Spot Instances to train deep learning models by using AWS Batch.
Apply basic AWS security practices to ML solutions. - AWS Identity and Access Management (IAM)
- S3 bucket policies
- Security groups
- VPCs
- Encryption and anonymization
Deploy and operationalize ML solutions.

- Expose endpoints and interact with them.
- Understand ML models.
- Perform A/B testing.
- Retrain pipelines.
- Debug and troubleshoot ML models.

  • Detect and mitigate drops in performance.
  • Monitor performance of the model.
Your rating: None Rating: 4.9 / 5 (100 votes)