Deep Neural Learning Adaptive Sequential Monte Carlo for Automatic Image and Speech Recognition

Table 2

Results of the applied method and the gradient descent optimizer for speech recognition.

Method	Mean accuracy (%)	Mean cross entropy	Final test accuracy (%)
The applied method (50, 50)	77.8163	0.6772	89.693
The applied method (150, 100)	77.4286	0.6900	89.059
The applied method (180, 300)	77.2724	0.6952	89.141
The gradient descent method	77.4950	0.6853	89.325