← Return Home

ML Simulations

Interactive visualizations of machine learning concepts running directly in your browser.

CartPole Training

Episode: 0
Reward: 0
Best: 0
Avg(20): 0
σ: 0.25
Steps/s: 0
Runtime: 0.0s
Status: Idle
Weights: [0.00, 0.00, 0.00, 0.00]
⚙️ Configuration

Rewards track balanced timesteps per episode.

Linear Regression via Gradient Descent

Training a model to predict housing prices (Target) based on area (Feature).
Dataset: California Housing (Normalized)

Loss (MSE): 0.00 Epoch: 0

Left: The regression line (red) fitting the data points (blue). As loss decreases, the line aligns better with the data trend.

Linear regression is mathematically identical to a single-neuron neural network (with linear activation). Watch the weight (w) and bias (b) update in real-time as gradient descent optimizes them, just like in complex deep networks!

Try a high learning rate (> 0.5) to see divergence — the path will oscillate or fly off the landscape.

Linear Regression = Single Neuron

Cost Landscape (w, b)

Green circle = optimal parameters (global minimum). Red = current position. Yellow = descent path.

Residuals (Error)

🕸️

Sparse Autoencoder

📚

RAG

Open RAG Demo