Duration 3 days – 21 hrs
Overview
This course provides participants with hands-on experience using popular AI development platforms and tools, including Google AI Platform, AWS AI Services, and Azure AI Studio. Participants will also explore cloud-based coding environments like Google Colab and Jupyter Notebooks to build, test, and deploy basic AI models. The course is ideal for those looking to understand how enterprise-grade AI is developed and deployed on leading platforms.
Objectives
- Navigate major cloud-based AI platforms: Google Cloud AI, AWS AI, and Microsoft Azure AI
- Use Jupyter Notebooks and Google Colab for Python-based AI development
- Understand the core services offered by each cloud provider for machine learning and AI
- Run basic model training, evaluation, and deployment workflows on cloud platforms
- Compare platform features to choose the right tool for different AI project needs
Audience
- Data analysts, developers, and AI enthusiasts looking to use cloud-based AI services
- IT professionals and project managers evaluating AI tools for team adoption
- ML engineers transitioning from local to cloud-based development environments
- Students or professionals working on practical AI projects across different platforms
Prerequisites
- Basic Python programming experience
- Familiarity with machine learning workflows (data loading, training, prediction)
- Prior exposure to any AI or ML tool (e.g., scikit-learn, TensorFlow) is helpful
Course Content
Day 1: AI Platforms & Development Environments
Session 1: Cloud AI Platform Overview
- Introduction to cloud AI: key features and benefits
- Comparing Google AI Platform, AWS AI Services, and Azure AI Studio
- Common services: AutoML, vision APIs, NLP tools, and deployment workflows
Session 2: AI Development Tools – Colab and Jupyter
- Setting up Jupyter Notebooks and Google Colab
- Writing and running Python code in the cloud
- Data integration from cloud storage and APIs
- Hands-on: Build a basic classification model in Colab using scikit-learn
Day 2: Running AI Projects on Cloud Platforms
Session 3: Google Cloud AI Platform
- Using Vertex AI and BigQuery ML for model building
- Deploying and monitoring models
- Hands-on: Use a pretrained model for image or text processing
Session 4: AWS AI Services and Azure AI Studio
- Overview of AWS SageMaker and Rekognition / Comprehend
- Azure ML Studio and AI Builder in Power Platform
- Hands-on: Try AutoML or drag-and-drop modeling
Session 5: Comparison, Deployment, and Next Steps
- Choosing the right platform for the right use case
- Deployment and cost considerations
- Final activity: Design a cloud-based AI workflow using one platform
