Scribd
Upload
0 views1 page

Sample Ai Notes

The document provides an overview of Artificial Intelligence (AI), its subsets including Machine Learning, Deep Learning, and Natural Language Processing (NLP). It discusses key concepts such as Transformers and Retrieval-Augmented Generation (RAG), which enhance language models' performance. Additionally, it mentions vector databases that store embeddings for similarity search.

Uploaded by

rahulramasubramanian2008
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
0 views1 page

Sample Ai Notes

The document provides an overview of Artificial Intelligence (AI), its subsets including Machine Learning, Deep Learning, and Natural Language Processing (NLP). It discusses key concepts such as Transformers and Retrieval-Augmented Generation (RAG), which enhance language models' performance. Additionally, it mentions vector databases that store embeddings for similarity search.

Uploaded by

rahulramasubramanian2008
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd

Introduction to Artificial Intelligence

Artificial Intelligence (AI) is the field of computer science that focuses on creating systems capable
of performing tasks that normally require human intelligence. Examples include image recognition,
speech recognition, recommendation systems, and autonomous vehicles.

Machine Learning
Machine Learning is a subset of AI where algorithms learn patterns from data. The three main types
are supervised learning, unsupervised learning, and reinforcement learning.

Deep Learning
Deep Learning uses neural networks with multiple hidden layers. It performs well on computer
vision, natural language processing, and speech recognition tasks.

Natural Language Processing (NLP)


NLP enables computers to understand and generate human language. Common tasks include text
classification, sentiment analysis, question answering, summarization, and machine translation.

Transformers
Transformers use self-attention to process all words in parallel. Popular transformer models include
BERT and GPT. Self-attention helps the model understand relationships between words.

Retrieval-Augmented Generation (RAG)


A RAG system first retrieves relevant chunks from a knowledge base using vector embeddings and
semantic search. The retrieved context is then supplied to a language model, reducing
hallucinations and improving factual accuracy.

Vector Databases
Vector databases such as FAISS, Pinecone, and Chroma store embeddings and perform similarity
search using metrics like cosine similarity.

You might also like