Related Experiment Video
Updated: May 10, 2025
05:30
Large Scale Energy Efficient Sensor Network Routing Using a Quantum Processor Unit
Published on: September 8, 2023
452
Photonic Bayesian Neural Networks: Leveraging Programmable Noise for Robust and Uncertainty-Aware Computing
Yangyang Zhuge1,2,3, Zhihao Ren1,2,4, Zian Xiao1,2
1Department of Electrical and Computer Engineering, National University of Singapore, 4 Engineering Drive 3, Singapore, 117583, Singapore.
Advanced Science (Weinheim, Baden-Wurttemberg, Germany)
|April 28, 2025
Summary
Researchers developed a photonic Bayesian neural network (PBNN) that leverages device noise for robust computation. This new architecture enhances photonic neural networks (PNNs) for uncertainty-aware applications.
Area of Science:
- Photonics
- Artificial Intelligence
- Integrated Circuits
Background:
- Silicon photonic integrated circuits (Si-PICs) offer energy-efficient, high-bandwidth photonic neural networks (PNNs).
- Deterministic PNNs struggle with hardware noise and data uncertainty, limiting real-world applications.
- Current PNNs lack robustness against device fluctuations and cannot handle data uncertainty effectively.
Purpose of the Study:
- To propose a novel photonic Bayesian neural network (PBNN) architecture.
- To enhance the robustness and uncertainty handling capabilities of PNNs.
- To transform inherent device noise into a computational advantage.
Main Methods:
- Developed a PBNN architecture incorporating Bayesian principles.
- Utilized photonic-noise-based random number generators with Mach-Zehnder interferometers and micro-ring resonators.
- Leveraged experimentally extracted data for modeling and validation.
Main Results:
- Achieved up to 98% classification accuracy for handwritten digit recognition, matching conventional models.
- Demonstrated PBNN effectiveness in multimodal data processing, regression, and outlier detection.
- Showcased a scalable and energy-efficient architecture transforming photonic noise into computational value.
Conclusions:
- The proposed PBNN architecture enhances robustness and addresses uncertainty in photonic computing.
- This approach overcomes limitations of deterministic PNNs, enabling uncertainty-aware applications.
- The PBNN represents a significant advancement for real-world AI applications using silicon photonics.
Related Concept Videos
00:59Propagation of Uncertainty from Random Error
500
An experiment often consists of more than a single step. In this case, measurements at each step give rise to uncertainty. Because the measurements occur in successive steps, the uncertainty in one step necessarily contributes to that in the subsequent step. As we perform statistical analysis on these types of experiments, we must learn to account for the propagation of uncertainty from one step to the next. The propagation of uncertainty depends on the type of arithmetic operation performed on...
500
01:10Propagation of Uncertainty from Systematic Error
345
The atomic mass of an element varies due to the relative ratio of its isotopes. A sample's relative proportion of oxygen isotopes influences its average atomic mass. For instance, if we were to measure the atomic mass of oxygen from a sample, the mass would be a weighted average of the isotopic masses of oxygen in that sample. Since a single sample is not likely to perfectly reflect the true atomic mass of oxygen for all the molecules of oxygen on Earth, the mass we obtain from this...
345
00:59Uncertainty: Overview
387
In analytical chemistry, we often perform repetitive measurements to detect and minimize inaccuracies caused by both determinate and indeterminate errors. Despite the cares we take, the presence of random errors means that repeated measurements almost never have exactly the same magnitude. The collective difference between these measurements - observed values - and the estimated or expected value is called uncertainty. Uncertainty is conventionally written after the estimated or expected value.
387
00:54Uncertainty: Confidence Intervals
2.9K
The confidence interval is the range of values around the mean that contains the true mean. It is expressed as a probability percentage. The interpretation of a 95% confidence interval, for instance, is that the statistician is 95% confident that the true mean falls within the interval. The upper and lower limits of this range are known as confidence limits. The confidence limits for the true mean are estimated from the sample's mean, the standard deviation, and the statistical factor...
2.9K
01:17Ampere-Maxwell's Law: Problem-Solving
459
A parallel-plate capacitor with capacitance C, whose plates have area A and separation distance d, is connected to a resistor R and a battery of voltage V. The current starts to flow at t = 0. What is the displacement current between the capacitor plates at time t? From the properties of the capacitor, what is the corresponding real current?
To solve the problem, we can use the equations from the analysis of an RC circuit and Maxwell's version of Ampère's law.
For the first part of...
To solve the problem, we can use the equations from the analysis of an RC circuit and Maxwell's version of Ampère's law.
For the first part of...
459
03:37Uncertainty in Measurement: Accuracy and Precision
72.9K
Scientists typically make repeated measurements of a quantity to ensure the quality of their findings and to evaluate both the precision and the accuracy of their results. Measurements are said to be precise if they yield very similar results when repeated in the same manner. A measurement is considered accurate if it yields a result that is very close to the true or the accepted value. Precise values agree with each other; accurate values agree with a true value.
72.9K