用于硬件高效深度学习的紧凑型蝴蝶式硅光电神经芯片
A compact butterfly-style silicon photonic-electronic neural chip for hardware-efficient deep learning
摘要：
光学神经网络（ONN）具有高并行性、低延迟、低能耗等优点，是下一代神经计算的理想硬件平台。以前的ONN架构主要是为通用矩阵乘法（GEMM）设计的，导致不必要的大面积成本和高控制复杂度。在这里，我们超越了经典的GEMM为基础的ONNs，并提出了一个光学子空间神经网络（OSNN）架构，它的贸易的普遍性的重量表示较低的光学元件的使用，面积成本和能源消耗。我们设计了一个蝴蝶式的光电神经芯片来实现我们的OSNN，与基于GEMM的ONN相比，可训练的光学元件减少了7倍。此外，提供了硬件感知的训练框架，以最大限度地减少所需的器件编程精度，减少芯片面积，并提高噪声鲁棒性。我们的实验表明，我们的神经芯片在实际的图像识别任务的效用，显示出94.16%的测量精度可以实现在手写数字识别任务与3位的重量编程精度。
英文摘要：
The optical neural network (ONN) is a promising hardware platform for next-generation neurocomputing due to its high parallelism, low latency, and low energy consumption. Previous ONN architectures are mainly designed for general matrix multiplication (GEMM), leading to unnecessarily large area cost and high control complexity. Here, we move beyond classical GEMM-based ONNs and propose an optical subspace neural network (OSNN) architecture, which trades the universality of weight representation for lower optical component usage, area cost, and energy consumption. We devise a butterfly-style photonic-electronic neural chip to implement our OSNN with up to 7x fewer trainable optical components compared to GEMM-based ONNs. Additionally, a hardware-aware training framework is provided to minimize the required device programming precision, lessen the chip area, and boost the noise robustness. We experimentally demonstrate the utility of our neural chip in practical image recognition tasks, showing that a measured accuracy of 94.16% can be achieved in hand-written digit recognition tasks with 3-bit weight programming precision.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
