# Neural Random-Access Machines

arXiv: https://arxiv.org/abs/1511.06392 · HTML: https://mlsanity.com/paper/1511.06392/

## Key facts

- Cited by 34 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Nov 2015.

## Built on by (most cited first, 30 of 34)

- [Program Synthesis with Large Language Models](https://mlsanity.com/paper/2108.07732/) (2021)
- [Least-to-Most Prompting Enables Complex Reasoning in Large Language Models](https://mlsanity.com/paper/2205.10625/) (2022)
- [Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges](https://mlsanity.com/paper/2104.13478/) (2021)
- [Show Your Work: Scratchpads for Intermediate Computation with Language Models](https://mlsanity.com/paper/2112.00114/) (2021)
- [CodeRL: Mastering Code Generation through Pretrained Models and Deep Reinforcement Learning](https://mlsanity.com/paper/2207.01780/) (2022)
- [Combinatorial optimization and reasoning with graph neural networks](https://mlsanity.com/paper/2102.09544/) (2021)
- [Neural Networks and the Chomsky Hierarchy](https://mlsanity.com/paper/2207.02098/) (2022)
- [Neural Algorithmic Reasoning](https://mlsanity.com/paper/2105.02761/) (2021)
- [CodeChain: Towards Modular Code Generation Through Chain of Self-revisions with Representative Sub-modules](https://mlsanity.com/paper/2310.08992/) (2023)
- [Code Execution with Pre-trained Language Models](https://mlsanity.com/paper/2305.05383/) (2023)
- [How to transfer algorithmic reasoning knowledge to learn new algorithms?](https://mlsanity.com/paper/2110.14056/) (2021)
- [Pushdown Layers: Encoding Recursive Structure in Transformer Language Models](https://mlsanity.com/paper/2310.19089/) (2023)
- [Neural Approximation of Graph Topological Features](https://mlsanity.com/paper/2201.12032/) (2022)
- [Autoregressive Large Language Models are Computationally Universal](https://mlsanity.com/paper/2410.03170/) (2024)
- [UnweaveNet: Unweaving Activity Stories](https://mlsanity.com/paper/2112.10194/) (2021)
- [INDICT: Code Generation with Internal Dialogues of Critiques for Both Security and Helpfulness](https://mlsanity.com/paper/2407.02518/) (2024)
- [Robot Program Parameter Inference via Differentiable Shadow Program Inversion](https://mlsanity.com/paper/2103.14452/) (2021)
- [Evolutionary Training and Abstraction Yields Algorithmic Generalization of Neural Computers](https://mlsanity.com/paper/2105.07957/) (2021)
- [Differentiable Tree Operations Promote Compositional Generalization](https://mlsanity.com/paper/2306.00751/) (2023)
- [Rationalizing Predictions by Adversarial Information Calibration](https://mlsanity.com/paper/2301.06009/) (2023)
- [Learning Program Behavioral Models from Synthesized Input-Output Pairs](https://mlsanity.com/paper/2407.08597/) (2024)
- [BF++: a language for general-purpose program synthesis](https://mlsanity.com/paper/2101.09571/) (2021)
- [Neural Machine Translation for Code Generation](https://mlsanity.com/paper/2305.13504/) (2023)
- [State-Space Constraints Can Improve the Generalisation of the Differentiable Neural Computer to Input Sequences With Unseen Length](https://mlsanity.com/paper/2110.09138/) (2021)
- [Exact Learning of Arithmetic with Differentiable Agents](https://mlsanity.com/paper/2511.22751/) (2025)
- [Universal computation is intrinsic to language model decoding](https://mlsanity.com/paper/2601.08061/) (2026)
- [PAC-learning gains of Turing machines over circuits and neural networks](https://mlsanity.com/paper/2103.12686/) (2021)
- [Enhancing Reinforcement Learning with discrete interfaces to learn the Dyck Language](https://mlsanity.com/paper/2110.14350/) (2021)
- [Program Generation from Diverse Video Demonstrations](https://mlsanity.com/paper/2302.00178/) (2023)
- [Enhancing Length Extrapolation in Sequential Models with Pointer-Augmented Neural Memory](https://mlsanity.com/paper/2404.11870/) (2024)

## Abstract (arXiv)

In this paper, we propose and investigate a new neural network architecture called Neural Random Access Machine. It can manipulate and dereference pointers to an external variable-size random-access memory. The model is trained from pure input-output examples using backpropagation. We evaluate the new model on a number of simple algorithmic tasks whose solutions require pointer manipulation and dereferencing. Our results show that the proposed model can learn to solve algorithmic tasks of such type and is capable of operating on simple data structures like linked-lists and binary trees. For easier tasks, the learned solutions generalize to sequences of arbitrary length. Moreover, memory access during inference can be done in a constant time under some assumptions.