# Meta-Learning Deep Energy-Based Memory Models

arXiv: https://arxiv.org/abs/1910.02720 · HTML: https://mlsanity.com/paper/1910.02720/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Oct 2019.

## Built on by (most cited first, 11 of 11)

- [Pin the Memory: Learning to Generalize Semantic Segmentation](https://mlsanity.com/paper/2204.03609/) (2022)
- [Associative Memories via Predictive Coding](https://mlsanity.com/paper/2109.08063/) (2021)
- [Uniform Memory Retrieval with Larger Capacity for Modern Hopfield Models](https://mlsanity.com/paper/2404.03827/) (2024)
- [Hierarchical Associative Memory](https://mlsanity.com/paper/2107.06446/) (2021)
- [BayesPCN: A Continually Learnable Predictive Coding Associative Memory](https://mlsanity.com/paper/2205.09930/) (2022)
- [Energy-Based Learning for Cooperative Games, with Applications to Valuation Problems in Machine Learning](https://mlsanity.com/paper/2106.02938/) (2021)
- [Equilibrium Aggregation: Encoding Sets via Optimization](https://mlsanity.com/paper/2202.12795/) (2022)
- [Meta-Reinforcement Learning with Self-Modifying Networks](https://mlsanity.com/paper/2202.02363/) (2022)
- [Hebbian and Gradient-based Plasticity Enables Robust Memory and Rapid Learning in RNNs](https://mlsanity.com/paper/2302.03235/) (2023)
- [Detecting Objects with Context-Likelihood Graphs and Graph Refinement](https://mlsanity.com/paper/2212.12395/) (2022)
- [BambooKG: A Neurobiologically-inspired Frequency-Weight Knowledge Graph](https://mlsanity.com/paper/2510.25724/) (2025)

## Abstract (arXiv)

We study the problem of learning associative memory -- a system which is able to retrieve a remembered pattern based on its distorted or incomplete version. Attractor networks provide a sound model of associative memory: patterns are stored as attractors of the network dynamics and associative retrieval is performed by running the dynamics starting from a query pattern until it converges to an attractor. In such models the dynamics are often implemented as an optimization procedure that minimizes an energy function, such as in the classical Hopfield network. In general it is difficult to derive a writing rule for a given dynamics and energy that is both compressive and fast. Thus, most research in energy-based memory has been limited either to tractable energy models not expressive enough to handle complex high-dimensional objects such as natural images, or to models that do not offer fast writing. We present a novel meta-learning approach to energy-based memory models (EBMM) that allows one to use an arbitrary neural architecture as an energy model and quickly store patterns in its weights. We demonstrate experimentally that our EBMM approach can build compressed memories for synthetic and natural data, and is capable of associative retrieval that outperforms existing memory systems in terms of the reconstruction error and compression rate.