Generality of the results.
Summary of 616 simulations with various parameters, excluding SGD with label noise (see Table 2). (A) Fraction of active units normalized by the first timestep for all simulations. Red line is the mean. Note that all simulations exhibit a stochastic decrease in the fraction of active units. See Fig S1 for further breakdown. (B) Dependence of sparseness (top) and sparsification time scale (bottom) on noise amplitude. Each point is one of 178 simulations with the same parameters except noise variance. (C) Learning a similarity matching task with Hebbian and anti-Hebbian learning using published code from [24]. Performance of the network (blue) and fraction of active units (red) as a function of training steps. Note that the loss axis does not start at zero, and the dynamic range is small. The background colors indicate which phase is dominant throughout learning (1 - red, 2 - yellow, 3 - green).