One of the significant problem in robot kinematics is to optimising the solution of inverse kinematics which deals with obtaining the joint variables in terms of the end-effector position and orientation and is difficult than the forward kinematics problem. As the degree of freedom of a robot increases the inverse kinematics calculation become more difficult and expensive. This paper proposes neural network architecture to optimise the inverse kinematics solution.The neural networks ideasconsidered here are Time Delay and Distributed Time Delay Neural Network Algorithms. This technique causes a decrease in the difficulty and calculations faced when using the traditional methods in robotics. Thus the optimised output is evaluated to ensure the efficiency of this approach. © International Science Press.