小脑神经网络利用涡旋傅里叶编码器快速求解逆问题
Small-brain neural networks rapidly solve inverse problems with vortex Fourier encoders
AI总结：
提出涡旋傅里叶编码的浅层小脑神经网络，无需迭代或深度学习即可从强度数据高速重建低光照图像，在CPU上比卷积神经网络快两个数量级。
摘要：
我们引入了一种带有透镜阵列的涡旋相位变换，以配合浅层、密集的“小脑”神经网络，用于高速和低光照成像。我们的单次叠层成像方法利用了傅里叶变换螺旋相位梯度的相干衍射、紧凑表示和边缘增强。通过涡旋空间编码，训练小脑对图像进行反卷积，速度比随机编码方案快5-20倍，在存在噪声时优势更明显。训练完成后，小脑仅从强度数据重建物体，无需对每张图像进行迭代且不使用深度学习方案。借助这种混合的光学-数字、涡旋傅里叶编码的小脑方案，我们在15 W中央处理器上以每秒数千帧的速率重建了在低光通量（5 nJ/cm$^2$）照明下的MNIST Fashion物体，比卷积神经网络快两个数量级。
英文摘要：
We introduce a vortex phase transform with a lenslet-array to accompany shallow, dense, ``small-brain'' neural networks for high-speed and low-light imaging. Our single-shot ptychographic approach exploits the coherent diffraction, compact representation, and edge enhancement of Fourier-tranformed spiral-phase gradients. With vortex spatial encoding, a small brain is trained to deconvolve images at rates 5-20 times faster than those achieved with random encoding schemes, where greater advantages are gained in the presence of noise. Once trained, the small brain reconstructs an object from intensity-only data, solving an inverse mapping without performing iterations on each image and without deep-learning schemes. With this hybrid, optical-digital, vortex Fourier encoded, small-brain scheme, we reconstruct MNIST Fashion objects illuminated with low-light flux (5 nJ/cm$^2$) at a rate of several thousand frames per second on a 15 W central processing unit, two orders of magnitude faster than convolutional neural networks.
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。
