Machine Learning

A subset of AI that enables systems to learn from data

Fundamentals

Deep Learning

Neural networks with multiple layers for complex pattern recognition

Fundamentals

Neural Networks

Computing systems inspired by biological neural networks

Architecture

Transformer

Architecture using attention mechanisms for sequence processing

Architecture

Attention Mechanism

Technique allowing models to focus on relevant parts of input

Technique

Large Language Model (LLM)

Massive neural networks trained on vast text corpora

Models

Convolutional Neural Network (CNN)

Neural networks specialized for processing grid-like data

Architecture

Backpropagation

Algorithm for training neural networks by propagating errors backward

Training

Gradient Descent

Optimization algorithm to minimize loss functions

Training

Overfitting

When a model learns training data too well, including noise

Concepts

Regularization

Techniques to prevent overfitting and improve generalization

Technique

Transfer Learning

Reusing pre-trained models for new but related tasks

Technique

Fine-tuning

Adapting pre-trained models to specific tasks

Training

Reinforcement Learning

Learning through interaction with environment and rewards

Fundamentals

Computer Vision

Enabling computers to understand and interpret visual information

Application

Natural Language Processing (NLP)

Enabling computers to understand and generate human language

Application

Prompt Engineering

Crafting effective inputs to guide AI model outputs

Technique

GPT (Generative Pre-trained Transformer)

Family of language models using transformer architecture

Models

BERT (Bidirectional Encoder Representations)

Transformer model that reads text bidirectionally

Models

Generative Adversarial Network (GAN)

Two neural networks competing to generate realistic data

Architecture

Activation Function

Non-linear functions that determine neuron output

Components