Photonic Neural Networks (PNNs) are gaining significant interest in the research community due to their potential for high parallelization, low latency, and energy efficiency. PNNs compute using light, which leads to several differences in implementation when compared to electronics, such as the need to represent input features in the photonic domain before feeding them into the network. In this encoding process, it is common to combine multiple features into a single input to reduce the number of inputs and associated devices, leading to smaller and more energy-efficient PNNs. Although this alters the network's handling of input data, its impact on PNNs remains understudied. This paper addresses this open question, investigating the effect of commonly used encoding strategies that combine features on the performance and learning capabilities of PNNs. Here, using the concept of feature importance, we develop a mathematical methodology for analyzing feature combination. Through this methodology, we demonstrate that encoding multiple features together in a single input determines their relative importance, thus limiting the network's ability to learn from the data. Given some prior knowledge of the data, however, this can also be leveraged for higher accuracy. By selecting an optimal encoding method, we achieve up to a 12.3% improvement in accuracy of PNNs trained on the Iris dataset compared to other encoding techniques, surpassing the performance of networks where features are not combined. These findings highlight the importance of carefully choosing the encoding to the accuracy and decision-making strategies of PNNs, particularly in size or power constrained applications.

翻译：光子神经网络因其高并行性、低延迟和能效优势而受到研究界的广泛关注。光子神经网络利用光进行计算，与电子实现相比在具体实施上存在若干差异，例如需要在将输入特征馈入网络前将其转换至光子域表示。在此编码过程中，通常会将多个特征组合为单一输入，以减少输入数量及相关器件，从而构建更紧凑、更高能效的光子神经网络。尽管这会改变网络对输入数据的处理方式，但其对光子神经网络的影响尚未得到充分研究。本文针对这一开放性问题，探究了常用特征组合编码策略对光子神经网络性能与学习能力的影响。基于特征重要性的概念，我们建立了一套用于分析特征组合的数学方法。通过该方法，我们证明了将多个特征编码至同一输入会决定其相对重要性，从而限制网络从数据中学习的能力。然而，若具备一定的先验数据知识，该特性亦可被用于提升精度。通过选择最优编码方法，我们在Iris数据集上训练的光子神经网络实现了较其他编码技术最高12.3%的精度提升，其性能甚至超越了未进行特征组合的网络。这些发现凸显了在尺寸或功耗受限的应用场景中，审慎选择编码方式对光子神经网络精度与决策策略的重要性。