Abstract:
Deep learning (DL) has achieved state-of-the-art performance in many challenging problems. However, DL requires powerful hardware for both training and deployment, increa...Show MoreMetadata
Abstract:
Deep learning (DL) has achieved state-of-the-art performance in many challenging problems. However, DL requires powerful hardware for both training and deployment, increasing the cost and energy requirements and rendering large-scale applications especially difficult. Recognizing these difficulties, several neuromorphic hardware solutions have been proposed, including photonic hardware that can process information close to the speed of light and can benefit from the enormous bandwidth available on photonic systems. However, the effect of using these photonic-based neuromorphic architectures, which impose additional constraints that are not usually considered when training DL models, is not yet fully understood and studied. The main contribution of this paper is an extensive study on the feasibility of training deep neural networks that can be deployed on photonic hardware that employ sinusoidal activation elements, along with the development of methods that allow for successfully training these networks, while taking into account the physical limitations of the employed hardware. Different DL architectures and four datasets of varying complexity were used for extensively evaluating the proposed method.
Published in: IEEE Transactions on Emerging Topics in Computational Intelligence ( Volume: 5, Issue: 3, June 2021)