Road-Type Classification with Deep AutoEncoder

<div>Performance of DAE model at 5 hidden layers of size {49, 40, 31, 22, 13} on the encoder and decoder; and embedding space of size 4: (a) reconstruction error at increasing learning rates and (b) validation accuracy at increasing learning rates.</div>

Computational Intelligence and Neuroscience

fig5

Figure 5

Figure 5: Road-Type Classification with Deep AutoEncoder 