Deep Convolutional Extreme Learning Machine and Its Application in Handwritten Digit Classification

Table 2

Performance on MNIST (with only 10k training samples).

Algorithms	Training time (s)	Training accuracy		Testing accuracy
		Mean	Std	Mean	Std
ELM	102.6	0.9965	0.0013	0.9457	0.0017
LRF-ELM	179.8	0.9882	0.0058	0.9763	0.0034
DC-ELM	78.15	0.9802	0.0027	0.9803	0.0015
CNN	2031.5	0.9703	0.0017	0.9724	0.0013
DBN	2968.4	0.9872	0.0022	0.9632	0.0021