Day	Topic
1	The Data Engineering, Big Data, AI & ML and Data Analysis Ecosystem
	Python Syntax Review- what do we need to know?
	Introduction to Machine Learning, objectives and types
	Data Wrangling and cleaning with pandas
	Exploratory Data Analysis(EDA)
	Overfitting and Underfitting
	Variance, Co-variance, Correlation; Bias-Variance; Decomposition and Tradeoff
	Good v/s Bad data
	Feature Engineering Deep Dive
	Errors and Optimizations in Machine learning
	Model Training, Validation, and Deployment using Azure ML
2	History and purpose of Scikit-learn
	Overview of various Scikit-learn algorithms
	Using ScikitLearn for ML models- Classification [multiple algorithms- 8 algorithms- theoretically discussed]
	KMeans and KNN
	Hands-on with Scikit-Learn Models (Linear Regression, Decision Trees, Random Forest, etc.)
	Model Evaluation and Hyperparameter Optimization: Grid search v/s Random Search
	Selecting the best model
3	What is NLP?
	Importance of NLP in AI
	Key NLP Techniques and Algorithms
	The Hidden Art of Communication - Hidden Markov Model
	Parsing and Text Analysis
	Parsing in Depth: Goals and Techniques
	Stemming and Lemmatization with Spacy and Textacy
	Introduction to Cloud Services for NLP
	Named Entity Extraction
	Deep dive into Natural Language Toolkit (NLTK)
	Sentiment Analysis
	Designing an NLP pipeline with prebuilt models
4	Overview on Azure OpenAI Service
	Generative AI models and Azure OpenAI base models
	Azure OpenAI's language, code, and image capabilities
	Prompt Engineering
	Azure OpenAI's responsible AI practices and limited access policies
	Optimizing Azure OpenAI models' performance with Prompt Engineering
	Best practices for deploying Generative AI models at scale
	Use the Azure OpenAI Studio, console, or REST API to deploy a base model and test it in the Studio's playgrounds.
5	One day hackathon style capstone project activity supported by the trainer