2020 BRN Discussion, page-17995

I don't think we can afford to be too sanguine about memristors. They are touted as being suitable for neural networks including SNNs:

https://cdn.intechopen.com/pdfs/56580.pdf
Memristor Neural Network Design
Memristor, a two terminal nanosolid state nonvolatile resistive switching, can provide energy-efficient neuromorphic computing with its synaptic behavior. Crossbar architecture can be used to perform neural computations because of its high density and parallel computation. Thus, neural networks based on memristor crossbar will perform better in real world applications. In this chapter, the design of different neural network architectures based on memristor is introduced, including spiking neural networks, multilayer neural networks, convolution neural networks, and recurrent neural networks

Haven't read the article yet, so I don't know if they have the self-learning secret sauce.