Learning from Pseudo-Randomness With an Artificial Neural Network - Does God Play Pseudo-Dice?

TL;DR

This paper explores using neural networks to detect hidden correlations in pseudo-random data and questions whether fundamental randomness differs from pseudo-randomness, potentially challenging the notion that 'God plays dice.'

Contribution

It demonstrates neural networks' ability to learn and predict in highly random environments and proposes using this approach to test fundamental differences between quantum and pseudo-randomness.

Findings

Neural networks can learn correlations in pseudo-random data.

Neural networks show high sensitivity in detecting hidden patterns.

Potential to test fundamental randomness assumptions.

Abstract

Inspired by the fact that the neural network, as the mainstream for machine learning, has brought successes in many application areas, here we propose to use this approach for decoding hidden correlation among pseudo-random data and predicting events accordingly. With a simple neural network structure and a typical training procedure, we demonstrate the learning and prediction power of the neural network in extremely random environment. Finally, we postulate that the high sensitivity and efficiency of the neural network may allow to critically test if there could be any fundamental difference between quantum randomness and pseudo randomness, which is equivalent to the question: Does God play dice?