On the validity of memristor modeling in the neural network literature
This critique highlights a fundamental modeling error in the memristive neural network literature, potentially invalidating many prior results.
The paper identifies that many publications use non-memristive models incorrectly labeled as memristive in neural networks, showing these models lack memory and are irrelevant to true memristive systems.
An analysis of the literature shows that there are two types of non-memristive models that have been widely used in the modeling of so-called "memristive" neural networks. Here, we demonstrate that such models have nothing in common with the concept of memristive elements: they describe either non-linear resistors or certain bi-state systems, which all are devices without memory. Therefore, the results presented in a significant number of publications are at least questionable, if not completely irrelevant to the actual field of memristive neural networks.