Outcome: By the end of the week, students will have a solid grasp of Python syntax, control flow, and data structures essential for data manipulation. They will be familiar with basic programming techniques and data manipulation using NumPy and Pandas required for data science workflows.

Outcome: Students will understand the fundamental calculus concepts such as derivatives and integrals, and their applications in optimization and machine learning model training.

Outcome: Students will gain a solid foundation in probability theory, crucial for understanding machine learning models, data distributions, and uncertainty in predictions.

Outcome: Students will learn to summarize and interpret data, conduct hypothesis tests, and analyze correlations in datasets, giving them the skills to draw meaningful conclusions from data.

Outcome: Students will develop skills in data cleaning, preprocessing, and creating visualizations to extract insights from data. This week will help them prepare datasets for machine learning tasks effectively

Outcome: Students will gain practical experience in building classification models, including KNN, Logistic Regression, and SVMs. They will also learn how to evaluate model performance using classification metrics.

Outcome: Students will gain proficiency in applying linear and multiple regression techniques, along with regularization methods (Lasso, Ridge) to prevent overfitting, and extend their understanding to polynomial regression for non-linear data.

Outcome: Students will be able to apply clustering techniques like k-Means and hierarchical clustering to uncover patterns in data, and reduce the dimensionality of data using PCA.

Outcome: Students will understand the workings of decision trees and random forests, along with their practical applications in classification and regression tasks. They will learn how to tune hyperparameters for better performance.

Outcome:Outcome: Students will learn how to analyze and forecast time series data using ARIMA and seasonal decomposition techniques. They will gain hands-on experience in making predictions from time series data.

Outcome: Students will be proficient in building and training feedforward neural networks, understanding how backpropagation works, and implementing regularization techniques to prevent overfitting

Outcome:Students will gain practical experience in building CNN models from scratch for image classification tasks. They will also understand how to use transfer learning to leverage pre-trained models.

Outcome: Students will understand the structure and workings of graphs, and be able to apply graph neural networks for classification and prediction tasks on graph-structured data.

Outcome: Students will have a strong understanding of deep learning models for sequential data, including RNNs and LSTMs, and an introduction to transformer models for natural language processing.

Outcome: Students will be proficient in designing and implementing recommendation systems, using both collaborative and content-based filtering techniques, and combining them into hybrid systems.

Outcome: Students will understand the end-to-end process of managing machine learning models from version control to deployment, monitoring, and continuous integration. They will be able to apply MLOps principles to real-world AI/ML projects.

Outcome: Students will gain hands-on experience with deep generative models like VAEs and GANs, understanding how these models work and implementing them to generate realistic data, images, or content.

Outcome: Students will learn how LLMs are structured and gain practical skills in fine-tuning these models for custom tasks. They will be able to deploy LLMs for NLP tasks and integrate them into production-level applications.

Outcome: Students will develop a deep understanding of the transformer architecture and how it powers LLMs. They will gain practical skills in building and scaling transformers for complex NLP tasks

Outcome: Students will be able to craft and optimize prompts for various NLP tasks, leveraging LLMs in effective ways. They will also understand the ethical considerations surrounding the use of LLMs in real-world applications.

Outcome: Students will have hands-on experience in training and fine-tuning LLMs, tuning hyperparameters, and optimizing models for deployment in production environments.

Outcome: Students will develop practical skills in building semantic search systems and integrating them with generative models using RAG. They will be able to apply these techniques in information retrieval and conversational AI.

Outcome: Students will develop a comprehensive understanding of building applications using large language models, with a strong emphasis on practical implementation using LangChain.

Note: The specific capstone projects will be decided when we reach Week 20, based on the latest market requirements and trends in AI and ML, ensuring relevance to realworld applications.

Outcome: Students will complete a market-relevant, real-world capstone project, showcasing their AI and ML skills, and will receive valuable feedback from industry professionals.