Final Exam: ML Engineer

WHAT YOU WILL LEARN

• 

  apply data clustering models to perform predictive analysis
  

  apply random forests for predictive analytics
  

  apply the phases of a machine learning project
  

  build and manage machine learning pipelines with Azure Machine Learning Service
  

  build data pipelines that can be used for machine learning deployments
  

  build generalized low rank models using H2O and integrate them into a data science pipeline to make better predictions
  

  compare hosting environments for on-premise, hosted, and cloud deployment
  

  create, train, and deploy simple machine learning models using the Amazon SageMaker to
  

  define and identify different hybrid cloud adoption scenarios
  

  define Pearson's correlation measures and specify the possible ranges for Pearson's correlation
  

  define the predictive analytics and describe its process flow identify the business problems that can be resolved using predictive modeling
  

  define the security considerations involved in choosing to use a hybrid cloud strategy
  

  define the VM creation pipeline in the Azure Stack
  

  demonstrate the tree-based methods that can be used to implement regression and classification
  

  describe automated testing in software design and development
  

  describe AWS Services for hybrid cloud implementations
  

  describe Azure machine learning tools, services, and capabilities recall the machine learning tools, services, and capabilities provided by AWS
  

  describe conceptual Machine Learning Software architecture
  

  describe dimensions of architecture to maximize benefits and minimize overhead and costs
  

  describe how adopting an AI strategy requires proper expectations and buy-in
  

  describe Machine Learning reference architecture blocks
  

  describe personnel training and how an AI implementation requires training
  

  describe task runners in software design and development
  

  describe the architecture of Amazon SageMaker as well as the internal AWS components used in Amazon SageMaker with focus on algorithm, training, and hosting services
  

  describe the best practices for implementing predictive modeling
  

  describe the causes of technical debt
  

  describe the challenges facing management when developing an AI solution and how it can impact personnel
  

  describe the challenges facing management when developing an AI solution and how it can impact personnel describe the common elements of an organizational AI strategy
  

  describe the Display Status automation design principle describe the Human-Computer Collaboration automation design principle describe the Human Intervention automation design principle
  

  describe the features of Lex, Polly, and Transcribe and their roles in machine learning implementation
• 

  describe the Human-Computer Collaboration automation design principle describe the Human Intervention automation design principle
  

  describe the steps used in planning and designing machine learning algorithms
  

  describing Service Oriented Architecture Maturity and Adoption levels
  

  Design and refine a Machine Learning architecture for production readiness
  

  distinguish features and views of the 4+1 Architectural View
  

  distinguish the different cloud deployment models
  

  distinguish the three categories of machine learning software development patterns
  

  enable CI/CD for machine learning projects with Azure Pipelines
  

  identifying the elements of a consumer-driven contract
  

  identify methods for random sampling and use hypothesis testing, Chi-square tests, and correlation
  

  identify reference architectures and their capabilities
  

  identify the actions required in Layered Architect design
  

  identify the essential stages of machine learning processes that need to be adopted by enterprises
  

  identify the machine learning algorithm for a particular purpose
  

  implement AWS hybrid cloud implementation from the perspective of provisioning
  

  implement refactoring techniques
  

  implement scatter plots and describe the capability of scatter plots in facilitating predictions
  

  implement visualization for machine learning using Python
  

  launch the Microsoft Azure Machine Learning Studio and work with datasets, train models, and projects
  

  recall the critical processes that are involved in training machine learning models
  

  recognize the essential stages of machine learning processes that need to be adopted by enterprises
  

  recognize the predictive modeling process, including how to explore and understand data, prepare for and model data, and evaluate and deploy the model
  

  recognize the value proposition of code refactoring
  

  set up and work with Git to facilitate team-driven development and coordination across the enterprise
  

  specify methods that can be used to manage missing values and outliers in datasets
  

  use AWS Services for resource and deployment management
  

  use Logistic Regression for predictive analytics
  

  use the Amazon SageMaker to create, train, and deploy simple machine learning models
  

  work with Python Rope to implement code refactoring
  

  work with refactoring techniques