Characterizing Coherent Integrated Photonic Neural Networks under Imperfections

• URL: http://arxiv.org/abs/2207.10835v1
• Date: Fri, 22 Jul 2022 01:33:19 GMT
• Title: Characterizing Coherent Integrated Photonic Neural Networks under Imperfections
• Authors: Sanmitra Banerjee, Mahdi Nikdast, Krishnendu Chakrabarty
• Abstract summary: Integrated photonic neural networks (IPNNs) are emerging as promising successors to conventional electronic AI accelerators. In this paper, we systematically characterize the impact of uncertainties and imprecisions in IPNNs using a bottom-up approach.
• Score: 7.387054116520716
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Integrated photonic neural networks (IPNNs) are emerging as promising successors to conventional electronic AI accelerators as they offer substantial improvements in computing speed and energy efficiency. In particular, coherent IPNNs use arrays of Mach-Zehnder interferometers (MZIs) for unitary transformations to perform energy-efficient matrix-vector multiplication. However, the underlying MZI devices in IPNNs are susceptible to uncertainties stemming from optical lithographic variations and thermal crosstalk and can experience imprecisions due to non-uniform MZI insertion loss and quantization errors due to low-precision encoding in the tuned phase angles. In this paper, we, for the first time, systematically characterize the impact of such uncertainties and imprecisions (together referred to as imperfections) in IPNNs using a bottom-up approach. We show that their impact on IPNN accuracy can vary widely based on the tuned parameters (e.g., phase angles) of the affected components, their physical location, and the nature and distribution of the imperfections. To improve reliability measures, we identify critical IPNN building blocks that, under imperfections, can lead to catastrophic degradation in the classification accuracy. We show that under multiple simultaneous imperfections, the IPNN inferencing accuracy can degrade by up to 46%, even when the imperfection parameters are restricted within a small range. Our results also indicate that the inferencing accuracy is sensitive to imperfections affecting the MZIs in the linear layers next to the input layer of the IPNN.

Related papers

• EPIM: Efficient Processing-In-Memory Accelerators based on Epitome [78.79382890789607]
  We introduce the Epitome, a lightweight neural operator offering convolution-like functionality. On the software side, we evaluate epitomes' latency and energy on PIM accelerators. We introduce a PIM-aware layer-wise design method to enhance their hardware efficiency.
  arXiv  Detail & Related papers  (2023-11-12T17:56:39Z)
• Cal-DETR: Calibrated Detection Transformer [67.75361289429013]
  We propose a mechanism for calibrated detection transformers (Cal-DETR), particularly for Deformable-DETR, UP-DETR and DINO. We develop an uncertainty-guided logit modulation mechanism that leverages the uncertainty to modulate the class logits. Results corroborate the effectiveness of Cal-DETR against the competing train-time methods in calibrating both in-domain and out-domain detections.
  arXiv  Detail & Related papers  (2023-11-06T22:13:10Z)
• Analysis of Optical Loss and Crosstalk Noise in MZI-based Coherent Photonic Neural Networks [8.930237478906266]
  silicon-photonic-based neural network (SP-NN) accelerators have emerged as a promising alternative to electronic accelerators. In this paper, we comprehensively model the optical loss and crosstalk noise using a bottom-up approach. We show a high power penalty and a catastrophic inferencing accuracy drop of up to 84% for SP-NNs of different scales.
  arXiv  Detail & Related papers  (2023-08-07T02:01:18Z)
• Benign Overfitting in Deep Neural Networks under Lazy Training [72.28294823115502]
  We show that when the data distribution is well-separated, DNNs can achieve Bayes-optimal test error for classification. Our results indicate that interpolating with smoother functions leads to better generalization.
  arXiv  Detail & Related papers  (2023-05-30T19:37:44Z)
• Data efficiency and extrapolation trends in neural network interatomic potentials [0.0]
  We show how architectural and optimization choices influence the generalization of neural network interatomic potentials (NNIPs) We show that test errors in NNIP follow a scaling relation and can be robust to noise, but cannot predict MD stability in the high-accuracy regime. Our work provides a deep learning justification for the extrapolation performance of many common NNIPs.
  arXiv  Detail & Related papers  (2023-02-12T00:34:05Z)
• A Dimension-Augmented Physics-Informed Neural Network (DaPINN) with High Level Accuracy and Efficiency [0.20391237204597357]
  Physics-informed neural networks (PINNs) have been widely applied in different fields. We propose a novel dimension-augmented physics-informed neural network (DaPINN) DaPINN simultaneously and significantly improves the accuracy and efficiency of the PINN.
  arXiv  Detail & Related papers  (2022-10-19T15:54:37Z)
• Auto-PINN: Understanding and Optimizing Physics-Informed Neural Architecture [77.59766598165551]
  Physics-informed neural networks (PINNs) are revolutionizing science and engineering practice by bringing together the power of deep learning to bear on scientific computation. Here, we propose Auto-PINN, which employs Neural Architecture Search (NAS) techniques to PINN design. A comprehensive set of pre-experiments using standard PDE benchmarks allows us to probe the structure-performance relationship in PINNs.
  arXiv  Detail & Related papers  (2022-05-27T03:24:31Z)
• Characterization and Optimization of Integrated Silicon-Photonic Neural Networks under Fabrication-Process Variations [8.690877625458324]
  Silicon-photonic neural networks (SPNNs) have emerged as promising successors to electronic artificial intelligence (AI) accelerators. The underlying silicon photonic devices in SPNNs are sensitive to inevitable fabrication-process variations (FPVs) stemming from optical lithography imperfections. We propose a novel variation-aware, design-time optimization solution to improve MZI tolerance to different FPVs in SPNNs.
  arXiv  Detail & Related papers  (2022-04-19T23:03:36Z)
• Mixed Precision Low-bit Quantization of Neural Network Language Models for Speech Recognition [67.95996816744251]
  State-of-the-art language models (LMs) represented by long-short term memory recurrent neural networks (LSTM-RNNs) and Transformers are becoming increasingly complex and expensive for practical applications. Current quantization methods are based on uniform precision and fail to account for the varying performance sensitivity at different parts of LMs to quantization errors. Novel mixed precision neural network LM quantization methods are proposed in this paper.
  arXiv  Detail & Related papers  (2021-11-29T12:24:02Z)
• Performance of teleportation-based error correction circuits for bosonic codes with noisy measurements [58.720142291102135]
  We analyze the error-correction capabilities of rotation-symmetric codes using a teleportation-based error-correction circuit. We find that with the currently achievable measurement efficiencies in microwave optics, bosonic rotation codes undergo a substantial decrease in their break-even potential.
  arXiv  Detail & Related papers  (2021-08-02T16:12:13Z)
• Modeling Silicon-Photonic Neural Networks under Uncertainties [4.205518884494758]
  Silicon-photonic neural networks (SPNNs) offer substantial improvements in computing speed and energy efficiency compared to their digital electronic counterparts. However, the energy efficiency and accuracy of SPNNs are highly impacted by uncertainties that arise from fabrication-process and thermal variations. We present the first comprehensive and hierarchical study on the impact of random uncertainties on the classification accuracy of a Mach-Zehnder Interferometer (MZI)-based SPNN.
  arXiv  Detail & Related papers  (2020-12-19T04:41:26Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.