Subtractive Perceptrons for Learning Images: A Preliminary Report

In recent years, artificial neural networks have achieved tremendous success for many vision-based tasks. However, this success remains within the paradigm of weak AI where networks, among others, are specialized for just one given task. The path toward 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 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.