Course Outline
Introduction
Setting Up ML.NET on the .NET Development Platform
- Configuring ML.NET tools and libraries.
- Identifying supported operating systems and hardware requirements.
ML.NET Features and Architecture Overview
- Exploring the ML.NET API.
- Reviewing supported machine learning algorithms and tasks.
- Introduction to probabilistic programming with Infer.NET.
- Selecting the right ML.NET dependencies for your project.
Introduction to ML.NET Model Builder
- Integrating Model Builder with Visual Studio.
- Leveraging AutoML capabilities within Model Builder.
Exploring the ML.NET Command-Line Interface (CLI)
- Automating machine learning model generation.
- Reviewing tasks supported via the ML.NET CLI.
Data Acquisition and Loading for Machine Learning
- Using the ML.NET API for data processing tasks.
- Defining and creating data model classes.
- Annotating data models for ML.NET.
- Scenarios for loading data into the ML.NET framework.
Preparing and Ingesting Data into ML.NET
- Applying ML.NET filter operations to data models.
- Working with DataOperationsCatalog and IDataView interfaces.
- Techniques for normalizing data during pre-processing.
- Handling data conversion within ML.NET.
- Processing categorical data for model generation.
Implementing ML.NET Algorithms and Tasks
- Binary and multi-class classification techniques.
- Applying regression models in ML.NET.
- Grouping instances using Clustering algorithms.
- Performing Anomaly Detection tasks.
- Ranking, Recommendation systems, and Forecasting models.
- Selecting the optimal algorithm for specific datasets.
- Executing data transformations in ML.NET.
- Techniques to boost model accuracy.
Training Machine Learning Models in ML.NET
- Constructing an ML.NET model structure.
- Utilizing ML.NET methods for model training.
- Splitting datasets for training and testing phases.
- Handling various data attributes and scenarios.
- Caching datasets to optimize training performance.
Evaluating ML.NET Models
- Extracting parameters for retraining or inspection.
- Collecting and documenting model metrics.
- Analyzing overall model performance.
Inspecting Intermediate Data During Training
Interpreting Predictions with Permutation Feature Importance (PFI)
Saving and Loading Trained ML.NET Models
- Understanding ITransformer and DataViewScheme.
- Loading data from local and remote sources.
- Managing model pipelines in ML.NET.
Applying Trained Models for Analysis and Prediction
- Configuring data pipelines for inference.
- Performing single and batch predictions.
Optimizing and Retraining ML.NET Models
- Utilizing re-trainable algorithms.
- Processes for loading, extracting, and retraining models.
- Comparing parameters between retrained and original models.
Cloud Integration with ML.NET
- Deploying models via Azure Functions and Web APIs.
Troubleshooting Strategies
Summary and Conclusions
Requirements
- Familiarity with machine learning algorithms and relevant libraries.
- Proficiency in C# programming.
- Practical experience with .NET development environments.
- Foundational knowledge of data science tooling.
- Hands-on experience with basic machine learning applications.
Target Audience
- Data Scientists
- Machine Learning Developers
Testimonials (3)
I really liked the end where we took the time to play around with CHAT GPT. The room was not set up the best for this- instead of one large table a couple of small ones so we could get into small groups and brainstorm would have helped
Nola - Laramie County Community College
Course - Artificial Intelligence (AI) Overview
Working from first principles in a focused way, and moving to applying case studies within the same day
Maggie Webb - Department of Jobs, Regions, and Precincts
Course - Artificial Neural Networks, Machine Learning, Deep Thinking
That it was applying real company data. Trainer had a very good approach by making trainees participate and compete
