AWS Certified Machine Learning Specialty: Implementation and Operations Competency

  • 31m
  • 31 questions
The AWS Certified Machine Learning Specialty: Implementation and Operations Competency benchmark measures your ability to build machine learning solutions for performance, availability, scalability, and fault tolerance. A learner who scores high on this benchmark demonstrates that they have the skills to recommend appropriate machine learning algorithms for a given problem and apply basic AWS security practices to machine learning solutions.

Topics covered

  • analyze images and videos in applications to distinguish assets and extract meaningful information
  • conduct A/B testing for models trained on Amazon Reviews dataset using production variants
  • convert a data frame to a sparse matrix
  • demonstrate how to reduce cost while training machine learning algorithms using Spot instances
  • demonstrate how to run hyperparameter tuning jobs with SageMaker using Python and Amazon Reviews dataset
  • deploy a machine learning model using API endpoints
  • describe how to enhance applications by giving them a voice
  • describe how to monitor an AWS system using CloudWatch
  • describe the at rest and in-transit encryption approaches used for security in SageMaker
  • distinguish between various AWS data storage services
  • enumerate several built-in SageMaker algorithms
  • evaluate a trained machine learning algorithm
  • extract insights and patterns from unstructured text using natural language processing
  • identify the advantages and disadvantages of collaborative filtering
  • increase information accessibility of apps by introducing an AI-powered search engine
  • increase the usability of apps by adding speech-to-text features
  • monitor API usage in real-time
  • outline Amazon's real-life problem formulation practice for commercial use of recommender systems
  • outline how to create S3 buckets for data storage
  • perform data quality checks on Amazon Reviews dataset using Python and SageMaker
  • recognize the difference between various SageMaker data formats
  • tackle forecasting problems using DeepAR
  • work with Amazon Forecast to accurately forecast time series without any machine learning (ML) experience
  • work with Amazon Ground Truth for data labeling jobs
  • work with Amazon Textract to parse millions of documents in no time and integrate them with Augmented AI
  • work with BlazingText for optimized text classification capabilities
  • work with feature engineering and machine learning experimentations using Python and SageMaker
  • work with S3 buckets to read a dataset using Python and SageMaker
  • work with SageMaker data accessing approaches, including VPCs, IAM, logs, and monitoring
  • work with SageMaker's built-it semantic segmentation algorithms
  • work with seq2seq models in SageMaker for natural language processing (NLP)