Subtractive Perceptrons for Learning Images: A Preliminary Report
Abstract
In recent years, artificial neural networks have achieved tremendous success for many vision-based tasks. However, this success remains within the paradigm of \emph{weak AI} where networks, among others, are specialized for just one given task. The path toward \emph{strong AI}, or Artificial General Intelligence, remains rather obscure. One factor, however, is clear, namely that the feed-forward structure of current networks is not a realistic abstraction of the human brain. In this preliminary work, some ideas are proposed to define a \textit{subtractive Perceptron} (s-Perceptron), a graph-based neural network that delivers a more compact topology to learn one specific task. In this preliminary study, we test the s-Perceptron with the MNIST dataset, a commonly used image archive for digit recognition. The proposed network achieves excellent results compared to the benchmark networks that rely on more complex topologies.
Cite
@article{arxiv.1909.12933,
title = {Subtractive Perceptrons for Learning Images: A Preliminary Report},
author = {H. R. Tizhoosh and Shivam Kalra and Shalev Lifshitz and Morteza Babaie},
journal= {arXiv preprint arXiv:1909.12933},
year = {2019}
}
Comments
To appear in the 9th Intern. Conf. on Image Processing Theory, Tools and Applications (IPTA 2019), Istanbul, Turkey