Sparse　coding　has　high-performance　encoding　and　ability　to　express　images,　sparse　encoding　basis　vector　plays　a　crucial　role.　The　computational　complexity　of　the　most　existing　sparse　coding　basis　vectors　of　is　relatively　large.　In　order　to　reduce　the　computational　complexity　and　save　the　time　to　train　basis　vectors.　A　new　Hebbian　rules　based　method　for　computation　of　sparse　coding　basis　vectors　is　proposed　in　this　paper.　A　two-layer　neural　network　is　constructed　to　implement　the　task.　The　main　idea　of　our　work　is　to　learn　basis　vectors　by　removing　the　redundancy　of　all　initial　vectors　using　Hebbian　rules.　The　experiments　on　natural　images　prove　that　the　proposed　method　is　effective　for　sparse　coding　basis　learning.　It　has　the　smaller　computational　complexity　compared　with　the　previous　work.　©　2009　IEEE.