An Artificial Neural Network Architecture Based on Context Transformations in Cortical Minicolumns

TL;DR

This paper proposes a novel neural network architecture inspired by cortical minicolumns, enabling context transformation memory, which achieves competitive accuracy on MNIST with fewer samples, diverging from traditional convolutional models.

Contribution

It introduces a new architecture based on cortical minicolumns that incorporates context transformation memory, differing from conventional convolutional neural networks.

Findings

Achieves near-CNN accuracy on MNIST

Performs well with limited training samples

Introduces context transformation memory in neural architecture

Abstract

Cortical minicolumns are considered a model of cortical organization. Their function is still a source of research and not reflected properly in modern architecture of nets in algorithms of Artificial Intelligence. We assume its function and describe it in this article. Furthermore, we show how this proposal allows to construct a new architecture, that is not based on convolutional neural networks, test it on MNIST data and receive close to Convolutional Neural Network accuracy. We also show that the proposed architecture possesses an ability to train on a small quantity of samples. To achieve these results, we enable the minicolumns to remember context transformations.