In　this　paper,　several　criteria　are　obtained　for　the　existence　and　exponential　attractivity　of　a　unique　κ-almost　periodic　sequence　solution　of　discrete-time　bidirectional　neural　networks　(BNNs).　Our　results　generalize　the　corresponding　results　about　almost　periodic　sequence　solution　in　common　sense.　Finally,　computer　simulations　illustrate　the　dynamic　behavior　of　discrete-time　bidirectional　neural　networks.　It　is　shown　that　discretization　step　κ　affects　dynamical　characteristics　of　bidirectional　neural　networks　and　our　results　on　κ-almost　periodic　sequence　solution　lead　to　effective　estimates　of　continuous-time　neural　networks　during　real-time　computations.　©　2009　Elsevier　B.V.　All　rights　reserved.