Course Outline
Introduction
Installing and Configuring Machine Learning for .NET Development Platform (ML.NET) for Government Use
- Setting up ML.NET tools and libraries for government applications
- Operating systems and hardware components supported by ML.NET for government operations
Overview of ML.NET Features and Architecture for Government
- The ML.NET Application Programming Interface (ML.NET API) for government workflows
- ML.NET machine learning algorithms and tasks suitable for public sector needs
- Probabilistic programming with Infer.NET for enhanced decision-making in government
- Deciding on the appropriate ML.NET dependencies to support government projects
Overview of ML.NET Model Builder for Government Use
- Integrating the Model Builder into Visual Studio for government development environments
- Utilizing automated machine learning (AutoML) with Model Builder to streamline government data analysis
Overview of ML.NET Command-Line Interface (CLI) for Government Applications
- Automated machine learning model generation for government projects
- Machine learning tasks supported by ML.NET CLI to meet public sector requirements
Acquiring and Loading Data from Resources for Machine Learning in Government
- Utilizing the ML.NET API for data processing in government systems
- Creating and defining the classes of data models for government datasets
- Annotating ML.NET data models to ensure compliance with government standards
- Cases for loading data into the ML.NET framework for government applications
Preparing and Adding Data Into the ML.NET Framework for Government Use
- Filtering data models with ML.NET filter operations to meet government data requirements
- Working with ML.NET DataOperationsCatalog and IDataView for government data management
- Normalization approaches for ML.NET data pre-processing in government projects
- Data conversion in ML.NET to support government data formats
- Working with categorical data for ML.NET model generation in government applications
Implementing ML.NET Machine Learning Algorithms and Tasks for Government Use
- Binary and Multi-class ML.NET classifications for government datasets
- Regression in ML.NET to support government predictive analytics
- Grouping data instances with Clustering in ML.NET for government data segmentation
- Anomaly Detection machine learning task for identifying outliers in government data
- Ranking, Recommendation, and Forecasting in ML.NET to enhance government decision-making
- Choosing the appropriate ML.NET algorithm for a government data set and functions
- Data transformation in ML.NET to prepare government datasets
- Algorithms for improved accuracy of ML.NET models for government use
Training Machine Learning Models in ML.NET for Government Applications
- Building an ML.NET model for government projects
- ML.NET methods for training a machine learning model to meet government standards
- Splitting data sets for ML.NET training and testing in government environments
- Working with different data attributes and cases in ML.NET for government use
- Caching data sets for ML.NET model training to optimize government workflows
Evaluating Machine Learning Models in ML.NET for Government Use
- Extracting parameters for model retraining or inspecting in government applications
- Collecting and recording ML.NET model metrics to ensure transparency in government projects
- Analyzing the performance of a machine learning model to meet government accountability standards
Inspecting Intermediate Data During ML.NET Model Training Steps for Government Use
Utilizing Permutation Feature Importance (PFI) for Model Predictions Interpretation in Government Applications
Saving and Loading Trained ML.NET Models for Government Use
- ITTransformer and DataViewScheme in ML.NET to support government data storage
- Loading locally and remotely stored data for government use
- Working with machine learning model pipelines in ML.NET for government projects
Utilizing a Trained ML.NET Model for Data Analyses and Predictions in Government Applications
- Setting up the data pipeline for model predictions in government workflows
- Single and Multiple predictions in ML.NET to support government decision-making
Optimizing and Re-training an ML.NET Machine Learning Model for Government Use
- Re-trainable ML.NET algorithms to enhance government models over time
- Loading, extracting, and re-training a model to improve government data accuracy
- Comparing re-trained model parameters with previous ML.NET models for government projects
Integrating ML.NET Models with The Cloud for Government Use
- Deploying an ML.NET model with Azure functions and web API to support government cloud initiatives
Troubleshooting for Government Applications
Summary and Conclusion for Government Use
Requirements
- Proficiency in machine learning algorithms and libraries
- Strong command of the C# programming language
- Experience with .NET development platforms
- Basic understanding of data science tools for government use
- Experience with fundamental machine learning applications
Audience
- Data Scientists
- Machine Learning Developers
Testimonials (2)
the ML ecosystem not only MLFlow but Optuna, hyperops, docker , docker-compose
Guillaume GAUTIER - OLEA MEDICAL
Course - MLflow
I enjoyed participating in the Kubeflow training, which was held remotely. This training allowed me to consolidate my knowledge for AWS services, K8s, all the devOps tools around Kubeflow which are the necessary bases to properly tackle the subject. I wanted to thank Malawski Marcin for his patience and professionalism for training and advice on best practices. Malawski approaches the subject from different angles, different deployment tools Ansible, EKS kubectl, Terraform. Now I am definitely convinced that I am going into the right field of application.
