Landmark 2 stops to get here · leads to 2
Parameter
Learnable values (weights and biases) in a neural network that are adjusted during training to minimize loss.
Your route here
2 stops · basics first
- Machine Learning ✓ understood
Building systems that learn patterns from data instead of following hand-written rules, getting better at a task as they see more examples.
- Neural Network ✓ understood
A computational model inspired by biological neural networks, consisting of interconnected nodes (neurons) organized in layers that process information through weighted connections.
- Parameter · you are here ✓ understood
Picture it
Parameters
- Weights and biases inside the model
- Learned from data during training
- Billions in a large model
- Updated by gradient descent
Hyperparameters
- Settings chosen before training
- e.g. learning rate, batch size, layers
- Set by you or a tuning search
- Not updated by gradient descent
Where it sits
Explore nearby
Neural Networks Weight Learnable parameters connecting neurons in neural networks, determining the strength of connections. Neural Networks Bias A learnable offset added to neuron inputs, allowing the model to fit data that doesn't pass through the origin. Training Hyperparameter Configuration settings external to the model (learning rate, batch size) that must be set before training begins. Language & LLMs Neural Scaling Laws Empirical relationships showing how model performance improves predictably with model size, data, and compute. Training Training The process of fitting a model to data by repeatedly measuring how wrong its outputs are and adjusting its parameters to reduce that error.