# Bootstrapping Concept Formation in Small Neural Networks

arXiv: https://arxiv.org/abs/2110.13665 · HTML: https://mlsanity.com/paper/2110.13665/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 4 of its 87 references that are in the map.
- First posted on arXiv 26 Oct 2021.

## Builds on (most cited first, 4 of 4)

- [Deep Visual Foresight for Planning Robot Motion](https://mlsanity.com/paper/1610.00696/) (2016)
- [Symbol Emergence in Cognitive Developmental Systems: a Survey](https://mlsanity.com/paper/1801.08829/) (2018)
- [A Deep Learning Approach to Grasping the Invisible](https://mlsanity.com/paper/1909.04840/) (2019)
- [Autonomous Identification and Goal-Directed Invocation of Event-Predictive Behavioral Primitives](https://mlsanity.com/paper/1902.09948/) (2019)

## Built on by (most cited first, 1 of 1)

- [Benchmarking local Hebbian learning rules for memory storage and prototype extraction](https://mlsanity.com/paper/2605.01074/) (2026)

## Abstract (arXiv)

The question how neural systems (of humans) can perform reasoning is still far from being solved. We posit that the process of forming Concepts is a fundamental step required for this. We argue that, first, Concepts are formed as closed representations, which are then consolidated by relating them to each other. Here we present a model system (agent) with a small neural network that uses realistic learning rules and receives only feedback from the environment in which the agent performs virtual actions. First, the actions of the agent are reflexive. In the process of learning, statistical regularities in the input lead to the formation of neuronal pools representing relations between the entities observed by the agent from its artificial world. This information then influences the behavior of the agent via feedback connections replacing the initial reflex by an action driven by these relational representations. We hypothesize that the neuronal pools representing relational information can be considered as primordial Concepts, which may in a similar way be present in some pre-linguistic animals, too. This system provides formal grounds for further discussions on what could be understood as a Concept and shows that associative learning is enough to develop concept-like structures.