What does temperature do in an LLM?

Temperature controls the randomness of an LLM's output. Low temperature (e.g., 0.1) makes the model more focused and deterministic. High temperature (e.g., 1.5) makes it more creative and unpredictable.

How does linear regression work?

Linear regression finds the best straight line through data points by minimizing the sum of squared differences between predictions and actual values. It uses gradient descent to iteratively adjust the line's slope and intercept.

AI Lab

Q: What is a neural network?

A neural network is a computing system inspired by biological brains. It consists of layers of interconnected nodes (neurons) that learn patterns from data by adjusting connection weights during training.

Q: What is a decision boundary?

A decision boundary is the line or surface that a trained model uses to separate different classes of data. In the AI Lab, you can watch this boundary form in real-time as the neural network trains.

Q: What is a loss function?

A loss function measures how wrong the model's predictions are. During training, the model tries to minimize this value. A decreasing loss curve means the model is learning and improving.

Experiment with different types of AI models. Train a neural network, fit a regression, or tweak LLM parameters: all in your browser.

Traditional MLNeural NetworkLLM

Learning Rate0.10

SlowFast

Epochs200

Hidden Neurons

Activation

Dataset

What is a Neural Network?

A neural network is a series of connected “neurons” organized in layers. Each neuron takes weighted inputs, adds them up, passes the result through an activation function, and sends the output to the next layer. By adjusting the weights during training, the network learns to map inputs to outputs.

What is a Loss Function?

The loss function measures how far the network’s predictions are from the true labels. During training, the goal is to minimize this number. For classification tasks we commonly use binary cross-entropy, which penalizes confident wrong predictions more than uncertain ones.

What is a Decision Boundary?

The decision boundary is the line (or curve) that separates different classes in the input space. A single neuron can only draw a straight line, but a network with hidden layers can learn complex, non-linear boundaries—like the curves needed to separate circles or moons.

0.0000

Loss

0.0%

Accuracy

Epoch

See how these models are being adopted in the real world

Explore live statistics on AI adoption, coding trends, and enterprise spending.

View AI Trends

AI Lab

See how these models are being adopted in the real world

Ready to build with Swfte?