# Hippocampal formation-inspired probabilistic generative model

arXiv: https://arxiv.org/abs/2103.07356 · HTML: https://mlsanity.com/paper/2103.07356/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 127 references that are in the map.
- First posted on arXiv 12 Mar 2021.

## Builds on (most cited first, 17 of 17)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [World Models](https://mlsanity.com/paper/1803.10122/) (2018)
- [Reinforcement Learning and Control as Probabilistic Inference: Tutorial and Review](https://mlsanity.com/paper/1805.00909/) (2018)
- [3D Dynamic Scene Graphs: Actionable Spatial Perception with Places, Objects, and Humans](https://mlsanity.com/paper/2002.06289/) (2020)
- [Semantics for Robotic Mapping, Perception and Interaction: A Survey](https://mlsanity.com/paper/2101.00443/) (2021)
- [Emergence of grid-like representations by training recurrent neural networks to perform spatial localization](https://mlsanity.com/paper/1803.07770/) (2018)
- [A free energy principle for a particular physics](https://mlsanity.com/paper/1906.10184/) (2019)
- [Symbol Emergence in Cognitive Developmental Systems: a Survey](https://mlsanity.com/paper/1801.08829/) (2018)
- [Variational Attention for Sequence-to-Sequence Models](https://mlsanity.com/paper/1712.08207/) (2017)
- [Neuro-SERKET: Development of Integrative Cognitive System through the Composition of Deep Probabilistic Generative Models](https://mlsanity.com/paper/1910.08918/) (2019)
- [Topomap: Topological Mapping and Navigation Based on Visual SLAM Maps](https://mlsanity.com/paper/1709.05533/) (2017)
- [Improved and Scalable Online Learning of Spatial Concepts and Language Models with Mapping](https://mlsanity.com/paper/1803.03481/) (2018)
- [Online Spatial Concept and Lexical Acquisition with Simultaneous Localization and Mapping](https://mlsanity.com/paper/1704.04664/) (2017)
- [Spatial Concept-Based Navigation with Human Speech Instructions via Probabilistic Inference on Bayesian Generative Model](https://mlsanity.com/paper/2002.07381/) (2020)
- [Information-based Active SLAM via Topological Feature Graphs](https://mlsanity.com/paper/1509.08155/) (2015)
- [The whole brain architecture approach: Accelerating the development of artificial general intelligence by referring to the brain](https://mlsanity.com/paper/2103.06123/) (2021)
- [AHA! an 'Artificial Hippocampal Algorithm' for Episodic Machine Learning](https://mlsanity.com/paper/1909.10340/) (2019)

## Built on by (most cited first, 5 of 5)

- [Double Articulation Analyzer with Prosody for Unsupervised Word and Phoneme Discovery](https://mlsanity.com/paper/2103.08199/) (2021)
- [A Whole Brain Probabilistic Generative Model: Toward Realizing Cognitive Architectures for Developmental Robots](https://mlsanity.com/paper/2103.08183/) (2021)
- [Active Exploration based on Information Gain by Particle Filter for Efficient Spatial Concept Formation](https://mlsanity.com/paper/2211.10934/) (2022)
- [Brain-inspired probabilistic generative model for double articulation analysis of spoken language](https://mlsanity.com/paper/2207.02457/) (2022)
- [DEQ-MCL: Discrete-Event Queue-based Monte-Carlo Localization](https://mlsanity.com/paper/2404.13973/) (2024)

## Abstract (arXiv)

In building artificial intelligence (AI) agents, referring to how brains function in real environments can accelerate development by reducing the design space. In this study, we propose a probabilistic generative model (PGM) for navigation in uncertain environments by integrating the neuroscientific knowledge of hippocampal formation (HF) and the engineering knowledge in robotics and AI, namely, simultaneous localization and mapping (SLAM). We follow the approach of brain reference architecture (BRA) (Yamakawa, 2021) to compose the PGM and outline how to verify the model. To this end, we survey and discuss the relationship between the HF findings and SLAM models. The proposed hippocampal formation-inspired probabilistic generative model (HF-PGM) is designed to be highly consistent with the anatomical structure and functions of the HF. By referencing the brain, we elaborate on the importance of integration of egocentric/allocentric information from the entorhinal cortex to the hippocampus and the use of discrete-event queues.