Transformer
The Transformer is a neural network architecture based on self-attention mechanisms that processes all input positions in parallel. Introduced in 2017, it became the foundation for virtually all modern large language models and many vision models.
Understanding Transformer
The transformer is a neural network architecture introduced in the landmark 2017 paper "Attention Is All You Need" that replaced recurrent processing with self-attention mechanisms, enabling parallel computation across entire sequences. This design breakthrough eliminated the sequential bottleneck of RNNs and LSTMs, allowing models to capture long-range dependencies efficiently. Transformers consist of encoder and decoder stacks built from multi-head attention layers and feed-forward networks, with positional encodings providing sequence order information. The architecture powers virtually all modern large language models including GPT, BERT, LLaMA, and Gemini, as well as vision transformers for image understanding and diffusion models for image generation. Transformers scale remarkably well with increased data and compute, a property that has driven the rapid advancement of generative AI capabilities over recent years.
Category
Deep Learning
Is AI recommending your brand?
Find out if ChatGPT, Perplexity, and Gemini mention you when people search your industry.
Check your brand — $9Related Deep Learning Terms
Activation Function
An activation function is a mathematical function applied to a neuron's output to introduce non-linearity into a neural network. Common activation functions include ReLU, sigmoid, and tanh, each with different properties for gradient flow.
Adam Optimizer
Adam (Adaptive Moment Estimation) is an optimization algorithm that combines the benefits of AdaGrad and RMSProp. It adapts learning rates for each parameter using estimates of first and second moments of gradients.
Adapter Layers
Adapter layers are small trainable modules inserted into a pre-trained model to enable parameter-efficient fine-tuning. They allow task adaptation while keeping the original model weights frozen.
Attention Mechanism
An attention mechanism allows neural networks to focus on the most relevant parts of the input when producing each element of the output. Attention is the foundational innovation behind the Transformer architecture and modern large language models.
Autoencoder
An autoencoder is a neural network trained to compress input data into a compact representation and then reconstruct it. Autoencoders are used for dimensionality reduction, denoising, and learning latent representations.
Backpropagation
Backpropagation is the algorithm used to train neural networks by computing gradients of the loss function with respect to each weight. It propagates error signals backward through the network to update weights and minimize prediction errors.
Batch Normalization
Batch normalization is a technique that normalizes layer inputs across mini-batches during training to stabilize and accelerate neural network training. It reduces internal covariate shift and allows higher learning rates.
Batch Size
Batch size is the number of training examples used in one iteration of gradient descent. Larger batches provide more stable gradient estimates but require more memory, while smaller batches add beneficial noise.