AI & ML

CONTENTS

1. 1.Introduction to AI and Real-world Application

• History and evolution of AI

• AI applications in major tech companies (Google, Amazon, IBM, Microsoft)

• AI’s impact on industries and jobs

• AI documentaries and guided discussions

2. AI Fundamentals & Ethics

• Basics and types of AI

• AI goals and development lifecycle

• Significance of data in AI

• AI ethics and social implications

3. Version Control with Git & GitHub

• Git basics: repositories, commits, branches

• GitHub for collaboration and versioning

• Setup of mini-project repositories

4. Machine Learning & Data Science

• ML types, workflow, and use cases

• Data pipelines and deployment strategies

• Data Science introduction and daily life examples

5. Cloud Computing & AI Cloud Services

• Cloud models: IaaS, PaaS, SaaS

• Public cloud platforms: AWS, Azure, GCP

• AI/ML services and cloud-based deployment

6. Python for Data Science

• Python packages: NumPy, Pandas, Matplotlib, Seaborn

• Data visualization and analysis

• Environment setup and database connectivity

7. Data Analysis & Statistics

• EDA: univariate and multivariate analysis

• Probability, distributions, and hypothesis testing

• Correlation and covariance

8. Data Preprocessing

• Handling missing values and outliers

• Data transformation and feature engineering

• Normalization, standardization

9. ML Algorithms: Regression & Classification

• Linear, Polynomial, Random Forest, SVR

• Decision Trees, Logistic Regression, SVM

• Evaluation metrics: R2, RMSE, Accuracy, AUC-ROC

10. Deep Learning & Neural Networks

• Introduction to DL, TensorFlow, and Keras

• Building and training deep neural networks

• Model optimization and visualization with TensorBoard

11. Natural Language Processing (NLP)

• Text preprocessing, tokenization, stemming, lemmatization

• TF-IDF, word clouds

• Sentiment analysis using spaCy and TensorFlow

12. MLOps & Deployment 

• MLOps pipeline: versioning, monitoring, deployment

• Docker and containers

• Model deployment to cloud

13. Mini Projects & Industry Readiness

• Projects in Regression, Classification, NLP

• GitHub version control and weekly reviews

• Resume, cover letter preparation

• Internship interview readiness