Table 3.

Decoding errors between class pairs

	Hand (L) Hand (R)	Hand (L) Feet	Hand (L) Rest	Hand (R) Feet	Hand (R) Rest	Feet Rest
FBCSP	82	28	31	3	12	42
Deep	70	13	27	13	21	26
Shallow	99	3	34	5	37	73

Results for the High‐Gamma Dataset. Number of trials where one class was mistaken for the other for each decoding method, summed per class pair. The largest number of errors was between Hand (L) and Hand (R) for all three decoding methods, the second largest between Feet and Rest (on average across the three decoding methods). Together, these two class pairs accounted for more than 50% of all errors for all three decoding methods. In contrast, Hand (L and R) and Feet had a small number of errors irrespective of the decoding method used.