作为二值化神经形态网络的极化激元晶格
Polariton lattices as binarized neuromorphic networks
AI总结：
本研究提出基于激子-极化激元凝聚体晶格的二值化神经形态网络，利用极化激元的相干性与非线性实现高效并行二值运算，在图像与语音识别任务中性能优于现有极化激元系统及传统基准模型。
摘要：
我们提出了一种基于激子-极化激元凝聚体晶格的新型神经形态网络架构，该架构通过非共振光泵浦实现复杂互连与能量供给。该网络采用二值化框架，借助成对耦合凝聚体的空间相干性，每个神经元可执行二值运算；这种相干性源于极化激元的弹道传播，可确保高效的全网通信。由极化激元激子分量的非线性排斥驱动的二值神经元切换机制，相比连续权重神经网络具备计算效率与可扩展性优势。该网络支持并行处理，与串行或脉冲编码的二值系统相比提升了计算速度。我们使用多种数据集评估了系统性能，包括用于图像识别的MNIST数据集和用于语音识别任务的Speech Commands数据集。在两类任务中，所提系统均展现出超越现有极化激元神经形态系统的潜力：图像识别任务中，预测分类准确率高达97.5%，表现亮眼；语音识别任务中，系统在十类子集上取得了约68%的分类准确率，优于传统基准模型——带高斯混合模型的隐马尔可夫模型（Hidden Markov Model with Gaussian Mixture Model）。
英文摘要：
We introduce a novel neuromorphic network architecture based on a lattice of exciton-polariton condensates, intricately interconnected and energized through non-resonant optical pumping. The network employs a binary framework, where each neuron, facilitated by the spatial coherence of pairwise coupled condensates, performs binary operations. This coherence, emerging from the ballistic propagation of polaritons, ensures efficient, network-wide communication. The binary neuron switching mechanism, driven by the nonlinear repulsion through the excitonic component of polaritons, offers computational efficiency and scalability advantages over continuous weight neural networks. Our network enables parallel processing, enhancing computational speed compared to sequential or pulse-coded binary systems. The system's performance was evaluated using diverse datasets, including the MNIST dataset for image recognition and the Speech Commands dataset for voice recognition tasks. In both scenarios, the proposed system demonstrates the potential to outperform existing polaritonic neuromorphic systems. For image recognition, this is evidenced by an impressive predicted classification accuracy of up to 97.5%. In voice recognition, the system achieved a classification accuracy of about 68\% for the ten-class subset, surpassing the performance of conventional benchmark, the Hidden Markov Model with Gaussian Mixture Model.
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。
