ml-jku/hopfield-layers

Health v2 · maintenance only

Flags: no_releases no_license

Adoption not part of the score

1959 stars · 228 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

A PyTorch library implementing modern Hopfield networks with continuous states, whose update rule is equivalent to transformer attention. It provides Hopfield layers (HopfieldLayer, HopfieldPooling, Hopfield lookup) that can be integrated into deep learning architectures.

Use cases

• implement modern Hopfield networks in PyTorch
• replace or augment transformer attention heads with Hopfield layers
• analyze transformer attention as Hopfield network updates
• build deep learning models with associative memory layers
• classify immune repertoire data with Hopfield-based networks
• experiment with attention mechanisms from the Hopfield Networks is All You Need paper

When to choose

• you want to use or study modern Hopfield layers in PyTorch deep learning models
• you are reproducing or extending the Hopfield Networks is All You Need research
• you need associative memory layers with exponential storage capacity
• you want to experiment with alternatives to standard attention heads

When to avoid

• you need a production-grade, actively maintained attention library
• you want a general-purpose transformer implementation rather than research layers
• you do not use PyTorch
• you need commercial support or extensive documentation

Facets

library · maturity maintenance

machine-learning deep-learning deep-learning machine-learning python hopfield-networks attention-mechanism transformers pytorch research-code associative-memory natural-language-processing

Member repositories

For agents

markdown · JSON · MCP: product_card(name="ml-jku/hopfield-layers")