Skip to main content
. 2015 Dec 15;9:464. doi: 10.3389/fnins.2015.00464

Figure 5.

Figure 5

Benchmark results comparing three hardware systems. Each system is running 500 neurons. The hardware do not statistically significantly differ, but are all statistically significant improvements over no adaptation (p < 0.05; two-tailed t-test with Bonferroni correction; 400 samples per condition). Scatterplots show individual runs (with random jitter on the x-axis to avoid overlap), the shaded area is the mean plus or minus the standard deviation, and the 95% confidence interval of the mean is shown.