Dive into Learning Explore the rich courses offerings of MammothClub.

Test your knowledge with 50+ questions from the Experimentation section of the Databricks Certified Machine Learning Professional exam, including reading and writing Delta tables, viewing Delta table history and loading a previous version of a Delta table, and creating, overwriting, merging, and reading Feature Store tables in machine learning workflows.

Test your knowledge with 50+ questions from the Experimentation section of the Databricks Certified Machine Learning Professional certification. Find out if you’re ready to ace the exam — if you can manually log parameters, models, and evaluation metrics using MLflow, programmatically access and use data, metadata, and models from MLflow experiments, and perform experiment tracking workflows with model signatures and input examples.

Test your knowledge with 50+ questions from the Model Lifecycle Management section of the Databricks Certified Machine Learning Professional certification. Find out if you’re ready to ace the exam — can you describe an MLflow flavor and the benefits of using MLflow flavors, explain the advantages of using the pyfunc MLflow flavor, understand the process and benefits of including preprocessing logic and context in custom model classes and objects, describe the basic purpose and user interactions with the Model Registry, and programmatically register a new model or a new model version?

Test your knowledge with 50+ questions from the Model Lifecycle Management section of the Databricks Certified Machine Learning Professional certification. Find out if you’re ready to ace the exam — can you add metadata to a registered model and its versions, identify, compare, and contrast the available model stages, transition, archive, and delete model versions, implement automated testing in ML Continuous Integration and Continuous Delivery (CI/CD) pipelines, and automate the model lifecycle using Model Registry webhooks and Databricks Jobs?

Test your knowledge with 50+ questions from the Model Lifecycle Management section of the Databricks Certified Machine Learning Professional certification. Find out if you’re ready to ace the exam — can you explain the advantages of using job clusters over all-purpose clusters, create a job that triggers when a model transitions between stages given a scenario, connect a webhook with a job, identify which code block will trigger a given webhook, identify a use case for HTTP webhooks and where the webhook URL must come from, and list all webhooks as well as delete a webhook?

Test your knowledge with 50+ questions from the Model Deployment section of the Databricks Certified Machine Learning Professional certification. Find out if you’re ready to ace the exam — can you explain why batch deployment is the appropriate approach for the vast majority of deployment use cases, describe how batch deployment computes predictions and stores them for later use, identify the live serving benefits of querying precomputed batch predictions, recognize less performant data storage as a solution for certain other use cases, load registered models using load_model, and deploy a single-node model in parallel using spark_udf? And much more!

Test your knowledge with 50+ questions from the Solution and Data Monitoring section of the Databricks Certified Machine Learning Professional certification. Find out if you’re ready to ace the exam — can you compare and contrast label drift and feature drift, identify scenarios in which feature or label drift are likely to occur, explain concept drift and its impact on model efficacy, describe summary statistic monitoring as a simple solution for numeric feature drift, explain how mode, unique values, and missing values serve as simple solutions for categorical feature drift, compare tests as more robust monitoring solutions for numeric feature drift than simple summary statistics, compare tests as more robust monitoring solutions for categorical feature drift than simple summary statistics, compare and contrast Jensen–Shannon divergence and Kolmogorov–Smirnov tests for numerical drift detection, identify a scenario in which a chi-square test would be useful, describe the common workflow for measuring concept drift and feature drift, determine when retraining and deploying an updated model is a probable solution to drift, and test whether the updated model performs better on more recent data? And much more!

Build eCommerce decentralized apps with AssemblyScript and JavaScript!