In　this　paper,　we　investigate　Cohen-Grossberg-type　bidirectional　associative　memory　neural　networks　with　transmission　delays　and　an　unsupervised　Hebbian-type　learning　behavior.　By　using　the　properties　of　an　M-matrix　and　Laypunov-Kravsovskii　functional,　some　new　sufficient　conditions　are　established　for　the　existence,　uniqueness　and　global　p-exponential　stability　of　a　unique　equilibrium　without　strict　conditions　imposed　on　self　regulation　functions.　The　obtained　sufficient　conditions　are　easy　to　verify　and　our　results　improve　the　previously　known　results.　©　2009　Korean　Society　for　Computational　and　Applied　Mathematics.