Quantum-noise-limited optical neural networks operating at a few quanta per activation.

A practical limit to energy efficiency in computation is ultimately from noise, with quantum noise [1] as the fundamental floor. Analog physical neural networks [2], which hold promise for improved energy efficiency and speed compared to digital electronic neural networks, are nevertheless typically operated in a relatively high-power regime so that the signal-to-noise ratio (SNR) is large (>10). We study optical neural networks [3] operated in the limit where all layers except the last use only a single photon to cause a neuron activation. In this regime, activations are dominated by quantum noise from the fundamentally probabilistic nature of single-photon detection. We show that it is possible to perform accurate machine-learning inference in spite of the extremely high noise (signal-to-noise ratio ~ 1). We experimentally demonstrated MNIST handwritten-digit classification with a test accuracy of 98% using an optical neural network with a hidden layer operating in the single-photon regime; the optical energy used to perform the classification corresponds to 0.008 photons per multiply-accumulate (MAC) operation, which is equivalent to 0.003 attojoules of optical energy per MAC. Our experiment also used >40× fewer photons per inference than previous state-of-the-art low-optical-energy demonstrations [4, 5] to achieve the same accuracy of >90%. Our training approach, which directly models the system's stochastic behavior, might also prove useful with non-optical ultra-low-power hardware.

An optical neural network using less than 1 photon per multiplication.

Deep learning has become a widespread tool in both science and industry. However, continued progress is hampered by the rapid growth in energy costs of ever-larger deep neural networks. Optical neural networks provide a potential means to solve the energy-cost problem faced by deep learning. Here, we experimentally demonstrate an optical neural network based on optical dot products that achieves 99% accuracy on handwritten-digit classification using ~3.1 detected photons per weight multiplication and ~90% accuracy using ~0.66 photons (~2.5 × 10-19 J of optical energy) per weight multiplication. The fundamental principle enabling our sub-photon-per-multiplication demonstration-noise reduction from the accumulation of scalar multiplications in dot-product sums-is applicable to many different optical-neural-network architectures. Our work shows that optical neural networks can achieve accurate results using extremely low optical energies.

[Impact of cigarette smoking on sperm quality and seminal plasma ROS in preconception males].

OBJECTIVE: To investigate the influence of cigarette smoking on sperm quality and ROS in the seminal plasma of preconception males in Chongqing so as to provide some guidance for preconception couples. METHODS: Totally, 368 preconception males were enrolled in this study, including 196 smokers and 172 non-smokers, and the former divided into mild smokers (n = 88, ≤9 cigarettes per day for ≤5 years) and moderate to heavy smokers (n = 108, ≥10 cigarettes per day for ≥5 years or ≤9 cigarettes per day for ≥10 years). All the subjects underwent physical examination, medical history interview, health questionnaire investigation, and determination of semen parameters, ROS in the seminal plasma and sperm DNA fragmentation index (DFI). RESULTS: Among the 368 preconception males, 53.26% had a history of cigarette smoking, of whom 29.35% were moderate to heavy smokers. Only 55.4% of the subjects were found with normal sperm morphology and 52.6% with normal sperm progressive motility. Compared with the non-smokers, the moderate to heavy smokers showed significantly decreased semen volume (ï¼»3.33 ± 1.20ï¼½ vs ï¼»2.78 ± 1.08ï¼½ ml, P < 0.05), sperm concentration (ï¼»88.19 ± 70.33ï¼½ vs ï¼»75.16 ± 60.13ï¼½ × 106/ml, P < 0.05), and percentages of progressively motile sperm (PMS, ï¼»36.58 ± 13.90ï¼½ % vs ï¼»32.18 ± 15.24ï¼½ %, P < 0.05) and morphologically normal sperm (MNS, ï¼»3.85 ± 1.93ï¼½ % vs ï¼»3.52 ± 1.58ï¼½ %, P < 0.05), but increased sperm DFI (ï¼»10.45 ± 8.53ï¼½ % vs ï¼»14.53 ± 12.85ï¼½ %, P < 0.05) and ROS in the seminal plasma (ï¼»12.20 ± 8.10ï¼½ vs ï¼»24.10 ± 18.50ï¼½ nmol/mg prot, P < 0.05). Cigarette smoking was correlated positively with the ROS level in the seminal plasma (r = 0.235, P < 0.05), while the ROS level of the smokers negatively with the total sperm count (r = －136, P < 0.05), PMS (r = －0.381, P < 0.01) and MNS (r = －0.218, P < 0.01), but positively with sperm DFI in the preconception males (r = 0.387, P < 0.01). CONCLUSIONS: Cigarette smoking can increase the ROS level in the seminal plasma, decrease the total sperm count and sperm progressive motility, and induce sperm malformation and sperm DNA fragmentation in preconception males.