MIT Press

Table 3:

MSE between the Target and Look Ahead Prediction.

	$w^{'}$
	1.0	0.5	0.25	0.15	0.1	0.01
1-step prediction	0.0101	0.00726	0.00418	0.00376	0.00341	0.00834
2-steps prediction	0.0171	0.0127	0.00907	0.00918	0.0116	0.0229
3-steps prediction	0.0222	0.0183	0.0140	0.0152	0.0205	0.0378
4-steps prediction	0.0279	0.0233	0.0189	0.0212	0.0301	0.0497
5-steps prediction	0.0325	0.0274	0.0234	0.0270	0.0375	0.0578

	$w^{'}$
	1.0	0.5	0.25	0.15	0.1	0.01
1-step prediction	0.0101	0.00726	0.00418	0.00376	0.00341	0.00834
2-steps prediction	0.0171	0.0127	0.00907	0.00918	0.0116	0.0229
3-steps prediction	0.0222	0.0183	0.0140	0.0152	0.0205	0.0378
4-steps prediction	0.0279	0.0233	0.0189	0.0212	0.0301	0.0497
5-steps prediction	0.0325	0.0274	0.0234	0.0270	0.0375	0.0578

Notes: The best predictions are produced by the model trained with an intermediate value of the meta-prior (⁠ $w^{'} = 0.25$ ⁠). The table shows the MSE between the unseen test targets and the one-step- to five-steps-ahead generated predictions. The networks with minimum MSE are shown in bold numbers.

View Large

This Feature Is Available To Subscribers Only