Bootstrapping Concept Formation in Small Neural Networks

10/26/2021
by   Minija Tamosiunaite, et al.
0

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. We argue that systems such as this can help formalizing the discussion about what constitutes Concepts and serve as a starting point for constructing artificial cogitating systems.

READ FULL TEXT

page 1

page 6

page 10

research
01/29/2020

Evaluating the Progress of Deep Learning for Visual Relational Concepts

Convolutional Neural Networks (CNNs) have become the state of the art me...
research
10/26/2020

Towards Concept Formation Grounded on Perception and Action of a Mobile Robot

The recognition of objects and, hence, their descriptions must be ground...
research
03/06/2019

Learning multimodal representations for sample-efficient recognition of human actions

Humans interact in rich and diverse ways with the environment. However, ...
research
04/19/2023

Learning Hierarchically-Structured Concepts II: Overlapping Concepts, and Networks With Feedback

We continue our study from Lynch and Mallmann-Trenn (Neural Networks, 20...
research
06/25/2012

The evolution of representation in simple cognitive networks

Representations are internal models of the environment that can provide ...
research
11/27/2018

Combining Deep Learning and Qualitative Spatial Reasoning to Learn Complex Structures from Sparse Examples with Noise

Many modern machine learning approaches require vast amounts of training...
research
10/05/2017

Stacked Structure Learning for Lifted Relational Neural Networks

Lifted Relational Neural Networks (LRNNs) describe relational domains us...

Please sign up or login with your details

Forgot password? Click here to reset