]>

Table 3: Details of the training procedure used for each of the benchmarking algorithms tested. In all cases the parameters values listed were those found to produce the best results. Parameter values were kept constant across variations in the task. All algorithms except use an online learning procedure and hence training time is measured in cycles, whereas for training time is measured in epochs. See the caption of Table 2 for further details.

Algorithm Training time Iterations Weight initialisation Parameter values 200 000 cycles n/a mean = , std = , 20 000 cycles 50 mean = , std = , , 2 000 epochs n/a mean = , std = , none 20 000 cycles 25 mean = , std = , 20 000 cycles 50 mean = , std =