Neural Stored-program Memory
Not on the map. Why?
Abstract (arXiv)
Neural networks powered with external memory simulate computer behaviors. These models, which use the memory to store data for a neural controller, can learn algorithms and other complex tasks. In this paper, we introduce a new memory to store weights for the controller, analogous to the stored-program memory in modern computer architectures. The proposed model, dubbed Neural Stored-program Memory, augments current memory-augmented neural networks, creating differentiable machines that can switch programs through time, adapt to variable contexts and thus resemble the Universal Turing Machine. A wide range of experiments demonstrate that the resulting machines not only excel in classical algorithmic problems, but also have potential for compositional, continual, few-shot learning and question-answering tasks.
Key facts. Cited by 14 papers in the map (data through 7 Oct 2026). First posted on arXiv 25 May 2019.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 5; 2022: 3; 2023: 3; 2024: 1; 2025: 1; 2026: 1.
14 papers.
Sort:
- 2022Content Addressable Memory Without Catastrophic Forgetting by Heteroassociation with a Fixed Scaffoldcited by 11
- 2021Object-Centric Representation Learning for Video Question Answeringcited by 7
- 2021Learning to Rehearse in Long Sequence Memorizationcited by 6
- 2021Evolutionary Training and Abstraction Yields Algorithmic Generalization of Neural Computerscited by 5
- 2023Learning Language Representations with Logical Inductive Biascited by 5
- 2022Learning to Constrain Policy Optimization with Virtual Trust Regioncited by 4
- 2023A Framework for Inference Inspired by Human Memory Mechanismscited by 2
- 2025Accelerating Long-Term Molecular Dynamics with Physics-Informed Time-Series Forecastingcited by 2
- 2021State-Space Constraints Can Improve the Generalisation of the Differentiable Neural Computer to Input Sequences With Unseen Lengthcited by 1
- 2026Continual Fine-Tuning of Large Language Models via Program Memorycited by 1
- 2021Memory Capacity of Recurrent Neural Networks with Matrix Representationcited by 0
- 2022Functional Indirection Neural Estimator for Better Out-of-distribution Generalizationcited by 0
2 more
- 2026Continual Fine-Tuning of Large Language Models via Program Memory13 May 2026
- 2025Accelerating Long-Term Molecular Dynamics with Physics-Informed Time-Series Forecasting16 Sep 2025
- 2024Enhancing Length Extrapolation in Sequential Models with Pointer-Augmented Neural Memory18 Apr 2024
- 2023Heterogenous Memory Augmented Neural Networks17 Oct 2023
- 2023A Framework for Inference Inspired by Human Memory Mechanisms1 Oct 2023
- 2023Learning Language Representations with Logical Inductive Bias19 Feb 2023
- 2022Functional Indirection Neural Estimator for Better Out-of-distribution Generalization23 Oct 2022
- 2022Learning to Constrain Policy Optimization with Virtual Trust Region20 Apr 2022
- 2022Content Addressable Memory Without Catastrophic Forgetting by Heteroassociation with a Fixed Scaffold1 Feb 2022
- 2021State-Space Constraints Can Improve the Generalisation of the Differentiable Neural Computer to Input Sequences With Unseen Length18 Oct 2021
- 2021Learning to Rehearse in Long Sequence Memorization2 Jun 2021
- 2021Evolutionary Training and Abstraction Yields Algorithmic Generalization of Neural Computers17 May 2021
2 more
- 2022Content Addressable Memory Without Catastrophic Forgetting by Heteroassociation with a Fixed Scaffoldcited by 11
- 2021Object-Centric Representation Learning for Video Question Answeringcited by 7
- 2021Learning to Rehearse in Long Sequence Memorizationcited by 6
- 2021Evolutionary Training and Abstraction Yields Algorithmic Generalization of Neural Computerscited by 5
- 2023Learning Language Representations with Logical Inductive Biascited by 5
- 2022Learning to Constrain Policy Optimization with Virtual Trust Regioncited by 4
- 2023A Framework for Inference Inspired by Human Memory Mechanismscited by 2
- 2025Accelerating Long-Term Molecular Dynamics with Physics-Informed Time-Series Forecastingcited by 2
- 2021State-Space Constraints Can Improve the Generalisation of the Differentiable Neural Computer to Input Sequences With Unseen Lengthcited by 1
- 2026Continual Fine-Tuning of Large Language Models via Program Memorycited by 1
- 2021Memory Capacity of Recurrent Neural Networks with Matrix Representationcited by 0
- 2022Functional Indirection Neural Estimator for Better Out-of-distribution Generalizationcited by 0
12 most cited of 14 All 14 (JSON)
- 2026Continual Fine-Tuning of Large Language Models via Program Memory13 May 2026
- 2025Accelerating Long-Term Molecular Dynamics with Physics-Informed Time-Series Forecasting16 Sep 2025
- 2024Enhancing Length Extrapolation in Sequential Models with Pointer-Augmented Neural Memory18 Apr 2024
- 2023Heterogenous Memory Augmented Neural Networks17 Oct 2023
- 2023A Framework for Inference Inspired by Human Memory Mechanisms1 Oct 2023
- 2023Learning Language Representations with Logical Inductive Bias19 Feb 2023
- 2022Functional Indirection Neural Estimator for Better Out-of-distribution Generalization23 Oct 2022
- 2022Learning to Constrain Policy Optimization with Virtual Trust Region20 Apr 2022
- 2022Content Addressable Memory Without Catastrophic Forgetting by Heteroassociation with a Fixed Scaffold1 Feb 2022
- 2021State-Space Constraints Can Improve the Generalisation of the Differentiable Neural Computer to Input Sequences With Unseen Length18 Oct 2021
- 2021Learning to Rehearse in Long Sequence Memorization2 Jun 2021
- 2021Evolutionary Training and Abstraction Yields Algorithmic Generalization of Neural Computers17 May 2021
12 newest of 14 All 14 (JSON)