In this paper, Particle Swarm Optimization-feedforward Neural Network (PSONN) and Genetic Algorithm-Neural Network (GANN) are proposed to enhance the learning process of ANN in term of convergence rate and classification accuracy. They have been tested and compared and the results applied in pattern classification. The experiments show that both algorithms produce feasible results in terms of convergence time and classification percentage. At the end of the evolutionary process of GANN for optimal structure, not only the best network structure for a particular application but also the trained network with few numbers of epochs is provided. A Hardware Design of ANN platform (HDANN) is proposed to evolve the architecture of ANN circuits using FPGA-spartan3 board (XSA-3S1000 Board). The HDANN design platform creates ANN design files using WebPACKTM ISE 9.2i, and converted into device-dependent programming files for eventual downloading into an FPGA device by using GXSLOAD program from the XSTOOLS programs.