Dropout

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.

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.

Rotary Positional Encoding

A position encoding method that encodes absolute position with a rotation matrix and naturally incorporates relative position information into attention computations.

A sequence modelling architecture based on continuous-time dynamical systems that processes long sequences with linear complexity, offering an alternative to attention-based transformers.

The automatic discovery of data representations needed for feature detection or classification from raw data.

A neural network architecture where connections between nodes form directed cycles, enabling processing of sequential data.

A neural network design where an encoder processes input into a fixed representation and a decoder generates output from it.

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

A distributed computing strategy that splits individual layer computations across multiple devices by partitioning weight matrices along specific dimensions.

A selective state space model that achieves transformer-level performance with linear-time complexity by incorporating input-dependent selection mechanisms into the recurrence.

Training a model on a large general dataset before fine-tuning it on a specific downstream task.

Overfitting

When a model learns the training data too well, including noise, resulting in poor performance on unseen data.

Regularisation

Techniques that add constraints or penalties to a model to prevent overfitting and improve generalisation to new data.