AI and ML

A deep-dive into Artificial Intelligence and Machine Learning

Machine Learning

Model trained using labeled data, meaning each input comes with a corresponding correct output

Examples:

Classification: Predicting categories (e.g., spam detection in emails, image recognition)
Regression: Predicting continuous values (e.g., stock price prediction, house price estimation)

Goal is to predict outcomes

Model trained on data without labeled outputs. It tries to find patterns, structures, or relationships within the data

Examples:

Clustering: Grouping similar data points (e.g., customer segmentation, anomaly detection)
Dimensionality Reduction: Reducing the number of variables in the dataset while preserving information (e.g., PCA for feature selection)

Goal is to find patterns

LLM (Large Language Models)
- Category of AI models that are trained on vast amounts of text data to understand and generate human-like text
GPT (Generative Pre-trained Transformer)
- A type of LLM:
  - Generative: It can create new text based on input prompts
  - Pre-trained: It learns from a large corpus of text before being fine-tuned for specific use cases
  - Transformer-based: Uses self-attention mechanisms to process words in context efficiently
RAG (Retrieval Augmented Generation)
- Data Retrieval - Knowledge graph or database
- Augmentation - Feeds data into generative model, reducing hallucinations
- Generation - Synthesizes info. into coherent, context-aware output
- Goals: Accuracy and Clarity

Helpful, Honest and Harmless