Standard 2 stops to get here · leads to 5
Weight
Learnable parameters connecting neurons in neural networks, determining the strength of connections.
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 model built from layers of simple units, each taking a weighted sum of its inputs and applying a nonlinearity; training adjusts the weights so the whole stack maps inputs to useful outputs.
- Weight · you are here ✓ understood
Where it sits
Before this
Neural Network Weight
Explore nearby
Neural Networks Parameter A number inside a model, a weight or a bias, that training adjusts to reduce the loss. Together, a model's parameters are everything it has learned. Neural Networks Bias A learnable offset added to neuron inputs, allowing the model to fit data that doesn't pass through the origin. Neural Networks Xavier Initialization A weight initialization strategy maintaining variance across layers, improving training of deep networks. Training Weight Decay A regularization technique that shrinks weights toward zero during optimization. Equivalent to L2 regularization in standard SGD, but differs when using adaptive optimizers like Adam. Neural Networks He Initialization Weight initialization designed for ReLU activations, preventing vanishing/exploding gradients in deep networks.