AI Fundamentals
Build your foundation in artificial intelligence through interactive visualizations
Foundation Concepts
Start here to build your base understanding
Perceptron & Linear Classification
Watch a perceptron learn to predict weather by drawing a line that separates rainy days from sunny days.
Data Preprocessing & Feature Engineering
Discover how data normalization and feature scaling dramatically improve learning.
Neural Network Building Blocks
Learn the core components that make networks work
Activation Functions Deep Dive
Compare ReLU, Sigmoid, and Tanh through interactive examples and see how they shape learning.
Neural Network Forward Pass
Follow data as it flows through layers of a trained network to make predictions.
Loss Functions & Metrics
Explore different loss functions and understand when to use each for classification vs regression.
Learning & Optimization
Understand how networks improve through training
Gradient Descent Optimization
See gradient descent navigate loss landscapes to find optimal solutions.
Backpropagation Step-by-Step
Watch gradients flow backward through layers and see how each weight gets updated.
Neural Network Training
Watch a neural network learn from scratch as random weights become intelligent through training.
Generalization & Robustness
Make your models work in the real world
Overfitting & Regularization
See how dropout and regularization help models generalize to new data.
Hyperparameter Tuning
Find the best learning rates, layer sizes, and settings for optimal performance.
Specialized Architectures
Explore networks designed for specific tasks
Convolutional Neural Networks (CNNs)
Watch convolutional filters detect edges, shapes, and patterns in images.
Recurrent Neural Networks (RNNs)
Watch RNNs process sequences by maintaining hidden states across time steps.
Embeddings & Representation Learning
Explore how neural networks learn to represent concepts as vectors in space.
Continue Your Journey
After completing AI Fundamentals, dive into modern architectures