DP-100

Azure Data Scientist Associate

Prepare for the DP-100 exam and demonstrate expertise in applying data science and machine learning to implement and run machine learning workloads on Azure.

76 lessons
14h 5m
4 modules
Loading...
Godlike Exams

Spend your points to unlock exam-style practice questions

The points you’re earning right now aren’t just for show — redeem them on Godlike Exams to unlock exam-style practice questions for the certifications you study here. Up to 20 questions per exam are free to try right away.

Browse practice exams

Course Content

4 modules · 76 lessons

Module 1: Design and Prepare a Machine Learning Solution

Design machine learning solutions and create/manage resources in Azure Machine Learning workspace. (20-25% of exam)

Design a Machine Learning Solution

Identify dataset structures and determine compute specifications for ML workloads.

Create and Manage Workspace Resources

Learn to create and manage Azure ML workspace datastores and compute targets.

Create and Manage Workspace Assets

Create and manage data assets environments and share assets across workspaces.

Module 2: Explore Data and Run Experiments

Use automated ML and notebooks for custom model training and hyperparameter tuning. (20-25% of exam)

Automated Machine Learning

Use AutoML for tabular data computer vision and NLP workloads.

Notebooks for Custom Model Training

Use notebooks and compute instances for custom model training with MLflow.

Hyperparameter Tuning

Automate hyperparameter tuning with sampling methods and early termination.

Module 3: Train and Deploy Models

Run model training scripts implement pipelines manage and deploy models. (25-30% of exam)

Running Model Training Scripts

Configure and run training scripts as jobs with proper data and compute configuration.

Implementing Training Pipelines

Create and run ML pipelines with custom components and data passing.

Managing Models

Register and manage MLflow models with responsible AI principles.

Deploying Models

Deploy models to online and batch endpoints for inference.

Module 4: Optimize Language Models for AI Applications

Prepare for optimization use prompt engineering RAG and fine-tuning. (25-30% of exam)

Prepare for Model Optimization

Select deploy and test language models from the model catalog.

Prompt Engineering and Prompt Flow

Optimize using prompt engineering variants templates and chaining.

Retrieval Augmented Generation (RAG)

Implement RAG solutions with data preparation and vector stores.

Fine-Tuning Language Models

Fine-tune language models for specific use cases.

Model Evaluation and AI Safety

Evaluate AI models and implement safety measures for responsible deployment.

Your Progress
Godlike Exams

Spend your points to unlock exam-style practice questions

Spend your points on exam-style practice questions.

Browse practice exams