# Neural Network based Formation of Cognitive Maps of Semantic Spaces and the Emergence of Abstract Concepts

arXiv: https://arxiv.org/abs/2210.16062 · HTML: https://mlsanity.com/paper/2210.16062/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 76 references that are in the map.
- First posted on arXiv 28 Oct 2022.

## Builds on (most cited first, 14 of 14)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Deep Learning: A Critical Appraisal](https://mlsanity.com/paper/1801.00631/) (2018)
- [word2vec Explained: deriving Mikolov et al.'s negative-sampling word-embedding method](https://mlsanity.com/paper/1402.3722/) (2014)
- [Performance-Efficiency Trade-offs in Unsupervised Pre-training for Speech Recognition](https://mlsanity.com/paper/2109.06870/) (2021)
- [Cognitive computational neuroscience](https://mlsanity.com/paper/1807.11819/) (2018)
- [How deep is deep enough? -- Quantifying class separability in the hidden layers of deep neural networks](https://mlsanity.com/paper/1811.01753/) (2018)
- [Learning with Known Operators reduces Maximum Training Error Bounds](https://mlsanity.com/paper/1907.01992/) (2019)
- [Known Operator Learning and Hybrid Machine Learning in Medical Imaging -- A Review of the Past, the Present, and the Future](https://mlsanity.com/paper/2108.04543/) (2021)
- [A statistical method for analyzing and comparing spatiotemporal cortical activation patterns](https://mlsanity.com/paper/1611.07677/) (2016)
- [A Tutorial on Network Embeddings](https://mlsanity.com/paper/1808.02590/) (2018)
- [Analysis of structure and dynamics in three-neuron motifs](https://mlsanity.com/paper/1811.05225/) (2018)
- [Neural Network based Successor Representations of Space and Language](https://mlsanity.com/paper/2202.11190/) (2022)
- [Will we ever have Conscious Machines?](https://mlsanity.com/paper/2003.14132/) (2020)
- [Integration of Leaky-Integrate-and-Fire-Neurons in Deep Learning Architectures](https://mlsanity.com/paper/2004.13532/) (2020)

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

- [Word class representations spontaneously emerge in a deep neural network trained on next word prediction](https://mlsanity.com/paper/2302.07588/) (2023)
- [Conceptual Cognitive Maps Formation with Neural Successor Networks and Word Embeddings](https://mlsanity.com/paper/2307.01577/) (2023)
- [Multi-Modal Cognitive Maps based on Neural Networks trained on Successor Representations](https://mlsanity.com/paper/2401.01364/) (2023)
- [Beyond Labels: Advancing Cluster Analysis with the Entropy of Distance Distribution (EDD)](https://mlsanity.com/paper/2311.16621/) (2023)
- [Analyzing Narrative Processing in Large Language Models (LLMs): Using GPT4 to test BERT](https://mlsanity.com/paper/2405.02024/) (2024)
- [Probing for Consciousness in Machines](https://mlsanity.com/paper/2411.16262/) (2024)
- [Polysemy of Synthetic Neurons Towards a New Type of Explanatory Categorical Vector Spaces](https://mlsanity.com/paper/2505.07831/) (2025)
- [Word-Class and Construction-Like Structure Emerges in Neural Successor Representations Trained on Natural Language](https://mlsanity.com/paper/2605.24585/) (2026)

## Abstract (arXiv)

The hippocampal-entorhinal complex plays a major role in the organization of memory and thought. The formation of and navigation in cognitive maps of arbitrary mental spaces via place and grid cells can serve as a representation of memories and experiences and their relations to each other. The multi-scale successor representation is proposed to be the mathematical principle underlying place and grid cell computations. Here, we present a neural network, which learns a cognitive map of a semantic space based on 32 different animal species encoded as feature vectors. The neural network successfully learns the similarities between different animal species, and constructs a cognitive map of 'animal space' based on the principle of successor representations with an accuracy of around 30% which is near to the theoretical maximum regarding the fact that all animal species have more than one possible successor, i.e. nearest neighbor in feature space. Furthermore, a hierarchical structure, i.e. different scales of cognitive maps, can be modeled based on multi-scale successor representations. We find that, in fine-grained cognitive maps, the animal vectors are evenly distributed in feature space. In contrast, in coarse-grained maps, animal vectors are highly clustered according to their biological class, i.e. amphibians, mammals and insects. This could be a possible mechanism explaining the emergence of new abstract semantic concepts. Finally, even completely new or incomplete input can be represented by interpolation of the representations from the cognitive map with remarkable high accuracy of up to 95%. We conclude that the successor representation can serve as a weighted pointer to past memories and experiences, and may therefore be a crucial building block for future machine learning to include prior knowledge, and to derive context knowledge from novel input.