Optimization of the structural complexity of artificial neural network for hardware-driven neuromorphic computing application

Abstract This work focuses on the optimization of structural complexity a single-layer feedforward neural network (SLFN) for neuromorphic hardware implementation. The singular value decomposition (SVD) method is used determination effective number neurons in hidden layer Modified National Institute Standards and Technology (MNIST) dataset classification. proposed also verified SLFN using weights derived from synaptic transistor device. effectiveness this methodology estimating reduced makes highly useful optimizing complex architectures their realization.