Model Components
Neural Network
Artificial neural networks (ANNs) are layered architectures of interconnected nodes (neurons). Each connection has a weight learned through backpropagation. Activation functions (ReLU, sigmoid) introduce nonlinearity enabling networks to approximate complex functions.
Neural networks form the foundation of all modern deep learning, from convolutional networks for vision to transformers for language. Their universal approximation capability means they can theoretically learn any continuous function given sufficient depth and data.
Authority Links
Related Terms
Core Concepts
Deep Learning
Subset of ML using neural networks with many layers to analyze complex data representations.
Techniques & Methods
Backpropagation
Training algorithm that adjusts neural network weights by propagating prediction errors backward through the network.
Model Components
Transformer
A neural-network architecture, introduced by Vaswani et al. in 2017, that uses self-attention and parallel computation across all sequence positions — the foundation under virtually every frontier language and multimodal model in production today.
Model Components
Parameter
A learnable variable within a model whose value is adjusted during training to minimize prediction error.