An Artificial Neural Network Architecture Based on Context Transformations in Cortical Minicolumns
This work addresses the gap in AI architectures for neuroscience-inspired models, but it appears incremental as it focuses on a specific domain application without broad SOTA impact.
The authors tackled the problem of incorporating cortical minicolumn models into AI by proposing a new neural network architecture based on context transformations, achieving close to CNN accuracy on MNIST and showing ability to train with small sample sizes.
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.