Table 1. Table of performance for benchmark datasets compared to published results on sparse networks.

We replicate the published architecture in each case for a fair comparison: For the original MNIST dataset and CIFAR-10 datasets, Mocanu et al (2018) [29] used three sparsely-connected layers of 1000 neurons each and 4% of possible connections existing. Pieterse & Mocanu (2019) [30] used the same architecture for the COIL-100 dataset. For the Fashion-MNIST dataset, Pieterse & Mocanu (2019) [30] used three sparsely-connected layers of 200 neurons each, with 20% of possible connections existing.

Dataset	Size			Accuracy
	Training	Test	Classes	Control (Source)	Normalisation
MNIST [40]	60, 000	10, 000	10	98.74% [29]	99.63%
Fashion-MNIST [41]	60, 000	10, 000	10	89.01% [30]	92.23%
CIFAR-10 [67]	50, 000	10, 000	10	74.84% [29]	77.43%
COIL-100 [68]	5, 764	1, 436	100	98.68% [30]	98.47%