Abstract

Contract Bridge is an intellectual game which motivates multiple skills and application of prior experience and knowledge, as no player knows accurately what moves other players are capable of making. The Bridge is a game played in the presence of imperfect information, yet its strategies must be well formulated, since the outcome at any intermediate stage is solely based on the choices made during the immediately preceding phase. In this paper, we train an Artificial Neural Network architecture using sample deals and use it to estimate the number of tricks to be taken by one pair of bridge players, which is the main challenge in the Double Dummy Bridge Problem. We focus on Back Propagation Neural Network Architecture with Back Propagation Algorithm with Sigmoidal transfer functions. We used two approaches namely, High – Card Point Count System and Distribution Point Method during the bidding phase of Contract Bridge. We experimented with two sigmoidal transfer functions namely, Log Sigmoid transfer function and the Hyperbolic Tangent Sigmoid function. Results reveal that the later performs better giving lower mean squared error on the output.