Realistic practice exam based on the most recent AWS Certified Machine Learning Specialty exam. Just like the actual exam this practice test has Test 1: 34 questions Test 2: 65 questions and takes 170 minutesQuestions are mapped based on the actual exam domains: Data EngineeringExploratory Data AnalysisModelingMachine Learning Implementation and Operations. Suggested background knowledgeData EngineeringAWS services: Glue, EMR ( Apache Spark, Hive metastore), AthenaKinesis family (Streams, data analytics, firehose, video streams) S3, QuickSightData/File formats (Avro, Parquet, CSV, protobuf recordIO)Exploratory Data AnalysisHandling missing values (Imputation: median, mean, most frequent, using ML model)Feature scalingFeature engineeringHandling outliersOne-hot encodingBinningText preprocessingModelingsupervised machine learning ( Classification and Regression Algorithms)unsupervised machine learning ( K-Means clustering, PCA)Hyperparameter tuning ( supervised machine learning, deep learning)Performance metrics ( accuracy, RMSE, F1 score, AUC, ROC, Precision, Recall)Tuning deep learning networks ( how to prevent overfitting)AWS MLservices: Lex, Polly, Transcribe, Translate, ComprehendSageMaker built-in algorithms: BlazingText, Object2Vec, DeepAR, LDA, Linear Learner, etc. ML Implementation and OperationsAmazon SageMaker train and deploy a modelInference pipeline, batch transform, inference endpoints, production variants, hosting servicesAmazon SageMaker security (data encryption at rest and in transit)Distributed training on Amazon SageMaker ( Using GPUs)AWS SageMaker rolesBring your own model container ( e.g. developed using scikit-learn)Customize SageMaker built-in algorithm containersHow to develop and deploy deep learning models on frameworks such as Tensoflow, MXNeT
