Attention Head

Self-Attention

An attention mechanism where each element in a sequence attends to all other elements to compute its representation.

Multi-Head Attention

An attention mechanism that runs multiple attention operations in parallel, capturing different types of relationships.

Residual Network

A deep neural network architecture using skip connections that allow gradients to flow directly through layers, enabling very deep networks.

Layer Normalisation

A normalisation technique that normalises across the features of each individual sample rather than across the batch.

Dropout

A regularisation technique that randomly deactivates neurons during training to prevent co-adaptation and reduce overfitting.

Activation Function

A mathematical function applied to neural network outputs to introduce non-linearity, enabling the learning of complex patterns.

ReLU

Rectified Linear Unit — an activation function that outputs the input directly if positive, otherwise outputs zero.

Sigmoid Function

An activation function that maps input values to a range between 0 and 1, useful for binary classification outputs.

Softmax Function

An activation function that converts a vector of numbers into a probability distribution, commonly used in multi-class classification.

Positional Encoding

A technique that injects information about the position of tokens in a sequence into transformer architectures.

Gradient Clipping

A technique that caps gradient values during training to prevent the exploding gradient problem.

Mixed Precision Training

Training neural networks using both 16-bit and 32-bit floating-point arithmetic to speed up computation while maintaining accuracy.

A deep learning architecture designed for processing structured grid data like images, using convolutional filters to detect features.

A form of model parallelism that splits neural network layers across devices and pipelines micro-batches through stages, maximising hardware utilisation during training.

A neural network layer that reduces spatial dimensions by aggregating values, commonly using max or average operations.

A problem in deep networks where gradients become extremely small during backpropagation, preventing earlier layers from learning.

A neural network component that learns to focus on relevant parts of the input when producing each element of the output.

A technique that normalises layer inputs during training to stabilise and accelerate deep neural network learning.

An IO-aware attention algorithm that reduces memory reads and writes by tiling the attention computation, enabling faster training of long-context transformer models.

A self-supervised learning approach that trains models by comparing similar and dissimilar pairs of data representations.