Feature　selection　is　an　important　data　preprocessing　for　machine　learning.　It　can　improve　the　performance　of　machine　learning　algorithms　by　removing　redundant　and　noisy　features.　Among　all　the　methods,　those　based　on　l1-norms　or　l2,1-norms　have　received　considerable　attention　due　to　their　good　performance.　However,　these　methods　cannot　produce　exact　row　sparsity　to　the　weight　matrix,　so　the　number　of　selected　features　cannot　be　determined　automatically　without　using　a　threshold.　To　this　end,　this　paper　proposes　a　feature　selection　method　incorporating　the　l2,0-norm,　which　can　guarantee　exact　row　sparsity　of　weight　matrix.　A　method　based　on　iterative　hard　thresholding　(IHT)　algorithm　is　also　proposed　to　solve　the　l2,0-　norm　regularized　least　square　problem.　For　fully　using　the　role　of　row-sparsity　induced　by　the　l2,0-norm,　this　method　acts　as　network　pruning　for　single-hidden-layer　neural　networks.　This　method　is　conducted　on　the　hidden　features　and　it　can　achieve　node-level　pruning　rather　than　the　connection-level　pruning.　The　experimental　results　in　several　public　data　sets　and　three　image　recognition　data　sets　have　shown　that　this　method　can　not　only　effectively　prune　the　useless　hidden　nodes,　but　also　obtain　better　performance.　©　2019　IEEE.