Week 12: Scientific AI Applications

AI transforming biology, chemistry, and scientific discovery

Time Estimate: 3-4 hours

Topics Covered

Featured Speaker

DM

DeepMind Team

Google DeepMind

Learn from industry leaders who are building the future of AI infrastructure and applications.

Video Resources

📹 Video content will be added here by Agent 2

Videos include keynotes, technical talks, and tutorials from industry leaders.

Reading Materials

📚 Reading list will be added here by Agent 3

Research papers, blog posts, and technical documentation.

🛠️ Hands-On Lab

Build a RAG Application

Beginner 3 hours

Objective

Create a retrieval-augmented generation system with embeddings, vector search, and LLM generation.

Prerequisites

  • Python 3.8+
  • Basic understanding of embeddings
  • Familiarity with LLM APIs
  • Google Colab free tier OK

Setup Instructions

  1. Install dependencies: pip install sentence-transformers faiss-cpu langchain
  2. Download a small document corpus (Wikipedia, arXiv papers)
  3. Set up OpenAI API key or use local model

Tasks

  1. Build document embeddings with sentence-transformers
  2. Create FAISS vector index for fast retrieval
  3. Implement retrieval component (top-k similar docs)
  4. Chain retrieval with LLM generation
  5. Compare retrieval strategies (dense vs sparse)
  6. Evaluate answer quality on test questions

Resources