# Generalisation of structural knowledge in the hippocampal-entorhinal system

arXiv: https://arxiv.org/abs/1805.09042 · HTML: https://mlsanity.com/paper/1805.09042/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 May 2018.

## Built on by (most cited first, 8 of 8)

- [Sequential Memory with Temporal Predictive Coding](https://mlsanity.com/paper/2305.11982/) (2023)
- [Dynamics of specialization in neural modules under resource constraints](https://mlsanity.com/paper/2106.02626/) (2021)
- [MSVIT: Improving Spiking Vision Transformer Using Multi-scale Attention Fusion](https://mlsanity.com/paper/2505.14719/) (2025)
- [Uncertainty-guided Compositional Alignment with Part-to-Whole Semantic Representativeness in Hyperbolic Vision-Language Models](https://mlsanity.com/paper/2603.22042/) (2026)
- [Predictive Learning in Energy-based Models with Attractor Structures](https://mlsanity.com/paper/2501.13997/) (2025)
- [Brain-Like Replay Naturally Emerges in Reinforcement Learning Agents](https://mlsanity.com/paper/2402.01467/) (2024)
- [JIR-Arena: The First Benchmark Dataset for Just-in-time Information Recommendation](https://mlsanity.com/paper/2505.13550/) (2025)
- [Vector Quantization in the Brain: Grid-like Codes in World Models](https://mlsanity.com/paper/2510.16039/) (2025)

## Abstract (arXiv)

A central problem to understanding intelligence is the concept of generalisation. This allows previously learnt structure to be exploited to solve tasks in novel situations differing in their particularities. We take inspiration from neuroscience, specifically the hippocampal-entorhinal system known to be important for generalisation. We propose that to generalise structural knowledge, the representations of the structure of the world, i.e. how entities in the world relate to each other, need to be separated from representations of the entities themselves. We show, under these principles, artificial neural networks embedded with hierarchy and fast Hebbian memory, can learn the statistics of memories and generalise structural knowledge. Spatial neuronal representations mirroring those found in the brain emerge, suggesting spatial cognition is an instance of more general organising principles. We further unify many entorhinal cell types as basis functions for constructing transition graphs, and show these representations effectively utilise memories. We experimentally support model assumptions, showing a preserved relationship between entorhinal grid and hippocampal place cells across environments.