QUESTPOND ONLINE COURSE

AI ML Step by Step Using C#, Python, Azure and OpenAI

What you'll learn

  • This training is designed for C#, .NET Developers who are new to AI ML.
  • It is 30+ Hours (3.5 Months) Live Training, will be conducted 2 hours a week.
  • Doubts Support related to the Training.
  • Recordings of the live sessions.
  • What are the pre-requisites ?
  • Good Internet Connection

Course Curriculum

Explore the topics covered in this course.

+
Introduction Road Map of AI ML for C# Developers. Click to view syllabus
Module 1
  • Lesson 1 (Theory) :- What is AI and ML?
  • Lesson 2 (Theory) :- How do Humans Learn ? :- Features and Labels. Alphabet Image Data Format
  • Lesson 3 (Theory) :- Features , Labels , Algo, Training , model :- FLATM
  • Lesson 4 (Lab 1) :- Understanding FLATM using simple EXCEL.
  • Lesson 5 (Theory) :- Algorithm ( Formula ) vs Model.
  • Lesson 6 (Theory) :- Defining regression. Regression
  • Lesson 7 (Lab 2) :- Simplest ML.NET Regression Code (Definition, MLContext ,& MKL components.)
  • Lesson 8 (Lab 3):- Model is an Mathematical Formula.
  • Lesson 9 (Theory) :- Inference VS Training
  • Lesson 10 (Theory) Road Map for AI ML
  • Lesson 11 (Theory) :- The psychology of ML.NET Code Pipeline.
  • Lesson 12 (Lab 4) :- Multi-Features Example and Algorithm Confusion.
  • Lesson 13 (Lab 5) :- OLS Ordinary Least Squares and SDCA Stochastic Dual Coordinate Ascent.
  • Lesson 14(Lab 6) :- R Square and RMSE ( Root Mean Squared)
  • Lesson 15 (Lab 7) :- AUTOML
  • Lesson 16 Theory :- Everything is a VECTOR.
  • Lesson 17 OLS with polynomial data
  • Lesson 18 AutoML and Cosine and Euclidean
  • Lesson 19 Feature Engineering.
  • Lesson 20 Linear , Non-Linear and Seasonal.
  • Lesson 21 Supervised Learning and Unsupervised Learning.
  • Lesson 22 Clustering Algorithms and KMeans
  • Lesson 23 What is MLP ?
  • Lesson 24 Vector , Tokens , Encoding,Embedding , Transformer , BERT and GPT ?
  • Lesson 25 MLP Encodings :- One-Hot Encoding , BOW , TF IDF , Word and Transformer Embeddings
  • Lesson 26 Prompt Engineering ( Personal , Task , Context , Constraints and Format)
  • Lesson 27 Data Quality (Descriptive Statistics, Outliers,,Min, Max, Median, Mode, Stdev, Skewness , Kurtosis, Quartiles )
+
Python Basic Lesson:- Click to view syllabus
Module 2
  • Lesson 28 :- Python basics comments , indents and blocks.
  • Lesson 29 :- Variable declaration and Dynamism.
  • Lesson 30 :- Simple For loops and Functions.
  • Lesson 31 :- Arrays in Python.
  • Lesson 32 :- Writing Classes , Functions and creating objects.
  • Lesson 33 :- Packages , Modules , Classes and OOP
  • Lesson 34 :- Numpy Fundamentals
  • Lesson 35 :- Pandas Fundamentals.
+
Machine Learning Labs in C# and Python :- Click to view syllabus
Module 3
  • Lesson 36 :- AUTOML
  • Lesson 37 :- Load Huge File and check AUTOML Suggestions and check Accuracy
  • Lesson 38 :- Saving model and retraining through Live training ( SDCA and Online Gradient Descent)
  • Lesson 39 :- Binary / Logistic regression.
  • Lesson 40 :- Multi Class Classification
  • Lesson 41 :- Simple Clustering Example using KMeans.
  • Lesson 42 :- Understanding One Hot Encoding.
  • Lesson 43 :- Simple Example of BOW
  • Lesson 44 :- Simple example of TF-IDF
  • Lesson 45 :- Example of WordEmbedding using GloVe50D and similarity checking using COSINE and Euclidean
  • Lesson 46 :- Simple BERT Example.
  • Lesson 47 :- GPT Example with Offline Encoding (Code does not work).
  • Lesson 48 :- ChatGPT Demonstrating Transformer.
  • Lesson 49 :- Simple RAG Demonstration
  • Lesson 50 :- Chunking
      1.Fixed Chunking ( overlap for connecting) :- LangChain.Splitters
      2.Sentence based Chunking. LangChain.Splitters
      3.Recursive based Chunking.( Paragraph → Line → Sentence → Word → Character)
      4.Semantic based Chunking.
      5.Hierarchical (Parent Child , Entity based , Lexical graph)
      6.Topic based.7.Modality based.8.Agentic Chunking.
    Neo4J
    Connecting the Chunks
    Overlap methodology ( Sliding window)
    Parent Child
    Contextual retrieval
    Graph based
    Meta Tagged
  • Lesson 51 :- Prompt Basics using ChatGpt
  • Lesson 52 :- Pytorch Fundamentals
  • Lesson 53 :- Creating a Model using Pytorch with simple Linear regression
  • Lesson 54 :- Creating Model using multiple Layers
  • Lesson 55 :- Consuming ONNX file.
  • Lesson 56 :- Understanding using Tensor flow.
+
Introduction to Azure AI Ecosystem Click to view syllabus
Module 4
  • Lesson 57 :- Creating Azure AI workspace, predicting simple linear regression using AUTOML
  • Lesson 58 :- Creating Model using Azure AI Designer (Inference Pipeline).
  • Lesson 59 :- Debugging AI issues in Azure.
  • Lesson 60 :- Creating model using Azure AI Notebook.
  • Lesson 61 :- Azure Foundry demo of Agents and Evals.

Setting Context :- MCP Model Context Protocol

+
Agent and Generative AI :- Click to view syllabus
Module 5
  • Lesson 62 :- Agentic AI with Semantic Kernel C#
  • Lesson 63 :- Agentic AI with Langchain , graph Python
  • Lesson 64 :- Simple N8N Demo with Manual trigger , Form trigger , Set fields , openAI and Webhooks.
  • Lesson 65 :- Data Quality
  • Lesson 66 :- MicroSoft Extension.AI
  • Lesson 67 :- Generative AI
+
Projects :- Click to view syllabus
Module 6

Dotnet Interview Mate and Nifty Prediction