Automatic Classification of Red Blood Cell Morphology Based on Quantitative Phase Imaging

Table 1

Parameter values of the algorithm in this article.

	Number of hidden neurons	Maximum times of iterations	Value of L2 regularization	Value of sparse regularization	Proportion of sparsity
SAE1	100	130	0.004	8	0.10
SAE2	50	70	0.004	8	0.10
Softmax layer	—	130	—	—	—