Module 1:
C#
🡫
- Introduction to C#
- Getting Started with C#
- Variables, Data Types & Type Safety
- Control Structure (Loop and If-else)
- Method Parameters
- C# Array and Type of Array
- String and String Builder
- OOPS Concept in depth
- Async/Await & Multithreading
- Exception Handling
- File Handling
- Delegate and Events
- Collection and Type of Collection
- Reflection and Extension class
Module 4: ML.NET Complete Course (30 Hours)
🡫
- Module 4.1: Introduction to Machine Learning (2 Hours)
- What is Machine Learning
- Types of Machine Learning (Supervised, Unsupervised)
- Real-world Applications of Machine Learning
- Introduction to ML.NET
- Advantages of ML.NET for .NET Developers
- Install ML.NET using NuGet Package
- Create First ML.NET Console Application
- Module 4.2: ML.NET Architecture and Core Components (3 Hours)
- ML.NET Workflow Overview
- Understanding MLContext
- Understanding IDataView
- Features and Labels
- Estimator and Transformer
- Training Pipeline Overview
- Module 4.3: Data Loading and Data Preparation (4 Hours)
- Load Data from CSV File
- Load Data from Database (SQL Server)
- Handling Missing Values
- Data Cleaning Techniques
- Feature Selection
- Data Normalization
- Convert Categorical Data into Numeric Data
- Module 4.4: Data Transformation and Feature Engineering (3 Hours)
- What is Feature Engineering
- OneHotEncoding in ML.NET
- Feature Concatenation
- Text Featurization
- Normalize Data using NormalizeMinMax
- Create Transformation Pipeline
- Module 4.5: Regression Models (4 Hours)
- What is Regression
- Regression Use Cases
- Linear Regression using ML.NET
- FastTree Regression
- Train Regression Model
- Evaluate Regression Model
- Salary Prediction Project Implementation
- Module 4.6: Classification Models (5 Hours)
- What is Classification
- Binary Classification
- Multi-class Classification
- Logistic Regression Model
- Decision Tree Model
- Random Forest Model
- Spam Detection Project using ML.NET
- Evaluate Classification Model Accuracy
- Module 4.7: Model Evaluation (2 Hours)
- Model Accuracy Concepts
- Confusion Matrix
- Precision and Recall
- F1 Score
- Improve Model Accuracy
- Module 4.8: Save and Load ML Model (2 Hours)
- Save Trained Model into File
- Load Model from File
- Reuse Model without Retraining
- Model Deployment Concepts
- Module 4.9: Real-Time Prediction (2 Hours)
- Create Prediction Engine
- Predict Real-Time Input Data
- Build Prediction Console Application
- Module 4.10: ML.NET with ASP.NET Core Web API (2 Hours)
- Create ASP.NET Core Web API
- Load ML Model in Web API
- Create Prediction Endpoint
- Test API using Postman
- Module 4.11: ML.NET with Database Integration (1 Hour)
- Load Data from SQL Server
- Train Model using Database Data
- Store Prediction Results in Database
- Module 4.12: Real-World Projects (2 Hours)
- Employee Salary Prediction System
- Product Recommendation System
- End-to-End ML.NET Project Implementation
