Track 5: Curriculum & Schedule

Finding and organizing project files, with emphasis on specifics of Mac and Windows systems

Key shortcuts and skills around command-line tools on Mac and Windows systems–automate the boring stuff

File naming, bulk renaming, and description

Setting up personal storage environment and cloud-storage clients, establishing backup systems

Installation of open-source software and understanding software dependencies

Understanding of how data files (text, tabular) store (encode) characters and sustainable ways to keep files usable over many years

Introduction to common formats for storing and collecting data (tabular, JSON, SQL)

Cleaning and transforming untidy data

Special case studies of spatial data files, image files, time-based media files–how they work and why they are more complex

dentify the ethical issues and data privacy risks associated with generative AI use

Think critically about generative AI use to support research and analyze the quality and accuracy of AI outputs

Explore NYU supported generative AI offerings

Evaluate Generative AI Tools for Academic Research 

Articulate the principles of Retrieval Augmented Generation (RAG) and its significance in enhancing AI models by integrating external data retrieval with large language models (LLMs).

Design and build a RAG pipeline, including steps such as embedding text into vector representations, retrieving relevant context from databases, and augmenting prompts to generate accurate responses.

Critically compare RAG with traditional fine-tuning approaches, analyzing the conditions and scenarios in which RAG is more advantageous for building context-aware AI systems.

Demonstrate proficiency in implementing RAG components through hands-on projects, showcasing the ability to troubleshoot and optimize retrieval-augmented generative solutions.