Hopfield Networks is All You Need

by   Hubert Ramsauer, et al.

We show that the transformer attention mechanism is the update rule of a modern Hopfield network with continuous states. This new Hopfield network can store exponentially (with the dimension) many patterns, converges with one update, and has exponentially small retrieval errors. The number of stored patterns is traded off against convergence speed and retrieval error. The new Hopfield network has three types of energy minima (fixed points of the update): (1) global fixed point averaging over all patterns, (2) metastable states averaging over a subset of patterns, and (3) fixed points which store a single pattern. Transformer and BERT models operate in their first layers preferably in the global averaging regime, while they operate in higher layers in metastable states. The gradient in transformers is maximal for metastable states, is uniformly distributed for global averaging, and vanishes for a fixed point near a stored pattern. Using the Hopfield network interpretation, we analyzed learning of transformer and BERT models. Learning starts with attention heads that average and then most of them switch to metastable states. However, the majority of heads in the first layers still averages and can be replaced by averaging, e.g. our proposed Gaussian weighting. In contrast, heads in the last layers steadily learn and seem to use metastable states to collect information created in lower layers. These heads seem to be a promising target for improving transformers. Neural networks with Hopfield networks outperform other methods on immune repertoire classification, where the Hopfield net stores several hundreds of thousands of patterns. We provide a new PyTorch layer called "Hopfield", which allows to equip deep learning architectures with modern Hopfield networks as a new powerful concept comprising pooling, memory, and attention. GitHub: https://github.com/ml-jku/hopfield-layers



There are no comments yet.



Of Non-Linearity and Commutativity in BERT

In this work we provide new insights into the transformer architecture, ...

Locally Shifted Attention With Early Global Integration

Recent work has shown the potential of transformers for computer vision ...

DeFormer: Decomposing Pre-trained Transformers for Faster Question Answering

Transformer-based QA models use input-wide self-attention – i.e. across ...

Efficient Visual Tracking with Exemplar Transformers

The design of more complex and powerful neural network models has signif...

Twins: Revisiting Spatial Attention Design in Vision Transformers

Very recently, a variety of vision transformer architectures for dense p...

What's Hidden in a One-layer Randomly Weighted Transformer?

We demonstrate that, hidden within one-layer randomly weighted neural ne...

Learning Attractor Dynamics for Generative Memory

A central challenge faced by memory systems is the robust retrieval of a...

Code Repositories


Hopfield Networks is All You Need

view repo
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.