On randomization of neural networks as a form of post-learning strategy

Abstract

Today artificial neural networks are applied in various fields -engineering, data analysis, robotics. While they represent a successful tool for a variety of relevant applications, mathematically speaking they are still far from being conclusive. In particular, they suffer from being unable to find the best configuration possible during the training process (local minimum problem). In this paper, we focus on this issue and suggest a simple, but effective, post-learning strategy to allow the search for improved set of weights at a relatively small extra computational cost. Therefore, we introduce a novel technique based on analogy with quantum effects occurring in nature as a way to improve (and sometimes overcome) this problem. Several numerical experiments are presented to validate the approach.

Multi-Sensor Integration Based on a New Quantum Neural Network Model for Land-Vehicle Navigation

“…Recent years saw the emergence of a new post-learning method that improves set of weights based on analogy with quantum effects occurring in nature. During the analogy, a biological neuron is simulated as a semiconductor heterostructure involving one energetic barrier sandwiched between two energetically lower areas (Kapanova et al, 2017). Compared to the traditional model, this new algorithm can be achieved with the minimal additional computing costs.…”