Skip to main content
. 2014 Dec 16;8:412. doi: 10.3389/fnins.2014.00412

Figure 4.

Figure 4

Influence of the synaptic resolution. (A) Examples of learned weight matrices with different numbers of constituents M per synapse. Even binary weights with only one stochastic switch learn to maintain a coarse image of prototypic digits. In the limit of large M, compound synapses support a quasi-continuous weight spectrum. (B) Classification error for different weight resolutions after 5000 s of learning, based on 20 independently trained networks for each value of M. Errorbars: SD among networks.