Discovering and Characterizing Hidden Variables Using a Novel Neural Network Architecture: LO-Net

Table 3

Simulated robot data (predicting 𝑥_𝑡+1): mean squared errors (MSEs).

HMM		LO-net
NO. of states	MSEs	MSE
100	0.004	0.0008
150	0.0036
200	0.0027
250	0.00086