Course Outline
Introduction
Installation and Configuration of Machine Learning for the .NET Development Platform (ML.NET)
- Initialization of ML.NET tools and libraries
Overview of ML.NET Features and Architecture
- The ML.NET Application Programming Interface (API)
- ML.NET machine learning algorithms and supported tasks
- Probabilistic programming via Infer.NET
Overview of ML.NET Model Builder
- Integration of Model Builder into Visual Studio
Overview of ML.NET Command-Line Interface (CLI)
- Automated generation of machine learning models
- Machine learning tasks supported by the ML.NET CLI
Data Acquisition and Loading for Machine Learning Resources
- Utilizing the ML.NET API for data processing workflows
- Creation and definition of data model classes
- Annotation of ML.NET data models
- Scenarios for data ingestion into the ML.NET framework
Data Preparation and Integration into the ML.NET Framework
- Filtering data models using ML.NET filter operations
- Utilizing ML.NET DataOperationsCatalog and IDataView components
- Normalization strategies for ML.NET data pre-processing
- Data conversion procedures within ML.NET
- Handling categorical data for ML.NET model generation
Implementation of ML.NET Machine Learning Algorithms and Tasks
- Binary and multi-class classification in ML.NET
- Regression analysis in ML.NET
- Data instance grouping via clustering in ML.NET
- Anomaly detection tasks
- Ranking, recommendation, and forecasting capabilities in ML.NET
- Selection of appropriate ML.NET algorithms for specific data sets and functions
- Data transformation techniques in ML.NET
- Algorithms for enhancing ML.NET model accuracy
Training Machine Learning Models in ML.NET
- Construction of an ML.NET model
- ML.NET methodologies for training machine learning models
- Partitioning data sets for ML.NET training and testing phases
- Management of various data attributes and scenarios in ML.NET
- Caching of data sets for ML.NET model training efficiency
Evaluation of Machine Learning Models in ML.NET
- Extraction of parameters for model retraining or inspection
- Collection and documentation of ML.NET model metrics
- Analysis of machine learning model performance
Inspection of Intermediate Data During ML.NET Model Training Steps
Application of Permutation Feature Importance (PFI) for Interpretation of Model Predictions
Saving and Loading Trained ML.NET Models
- Utilization of ITTransformer and DataViewScheme in ML.NET
- Retrieval of locally and remotely stored data
- Management of machine learning model pipelines in ML.NET
Application of Trained ML.NET Models for Data Analysis and Predictions
- Configuration of data pipelines for model predictions
- Execution of single and multiple predictions in ML.NET
Optimization and Retraining of ML.NET Machine Learning Models
- Re-trainable ML.NET algorithms
- Procedures for loading, extracting, and re-training models
- Comparison of re-trained model parameters with previous ML.NET models
Integration of ML.NET Models with Cloud Services
- Deployment of ML.NET models via Azure Functions and web APIs
Troubleshooting Protocols
Summary and Conclusion
Requirements
- Proficiency in machine learning algorithms and libraries
- Practical experience with .NET development platforms
- Fundamental understanding of data science toolsets
- Experience with basic machine learning application development
Audience
- Data Scientists
- Machine Learning Developers
Testimonials (2)
Getting people that never used AI some repetition in prompting and people that do use AI to consider different methods to using it.
Matthew Gay - Tarsus Pharmaceuticals
Course - Artificial Intelligence (AI) Overview
Working from first principles in a focused way, and moving to applying case studies within the same day
