Skip to Main Content
Table 3:
MSE between the Target and Look Ahead Prediction.
w'
1.00.50.250.150.10.01
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'
1.00.50.250.150.10.01
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.

Close Modal

or Create an Account

Close Modal
Close Modal