Input–Output BMI Models - Brain-Machine Interface Engineering - page 79

TaBlE 3.2: Average testing correlation coefficients as a

function of trajectory length

5 S/E 1 5 S/E 30 S/E 60 S/E

1 e/u 0.6514 0.7387 0.7302 0.7135

5 e/u 0.6458 0.7006 0.7263 0.7091

15 e/u 0.6544 0.7389 0.6680 0.6855

30 e/u 0.6807 0.7482 0.7116 0.6781

60 e/u 0.6457 0.6383 0.6772 0.6624

To test the effect of the initial condition on model performance, 100 Monte Carlo simulations
with different initial conditions were conducted with 20 010 consecutive bins (2001 sec) of neuronal
data to improve the chances of obtaining the global optimum. In Figure 3.12 , the training MSE is
presented for all simulations, and it can be seen that all initial conditions reach the approximately
the same solution. The greatest effect of the initial condition can be seen in the time it takes for each
model to converge. In Figure 3.13 , the average and standard deviations of the curves in Figure 3.12

FIgURE 3.12: Training MSE curves for 100 Monte Carlo simulations.