An application of the discrete Fourier transformation in simulating large neural networks

This paper presents an application of the discrete Fourier transform (DFT) to calculate neural activities efficiently in simulating large biologically motivated neural nets. The experimental results demonstrate the DFT technique is more superior in performing calculation of the neural activity which reduces the time complexity to a theoretical order of O(nlog₂, n), n being the number of neural units at each iteration. Our study also found that although the computational speed is improved drastically, there are tradeoffs involving: (1) the error generated from the transform, (2) initial setting up time, and (3) the memory storage requirement when using the DFT algorithm. More specifically, we outline criteria and conditions under which the DFT method will yield optimal results in large software neural simulations