# ROBIN: A Robust Optical Binary Neural Network Accelerator

arXiv: https://arxiv.org/abs/2107.05530 · HTML: https://mlsanity.com/paper/2107.05530/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 57 references that are in the map.
- First posted on arXiv 12 Jul 2021.

## Builds on (most cited first, 8 of 8)

- [Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation](https://mlsanity.com/paper/1308.3432/) (2013)
- [In-Datacenter Performance Analysis of a Tensor Processing Unit](https://mlsanity.com/paper/1704.04760/) (2017)
- [BinaryConnect: Training Deep Neural Networks with binary weights during propagations](https://mlsanity.com/paper/1511.00363/) (2015)
- [FINN: A Framework for Fast, Scalable Binarized Neural Network Inference](https://mlsanity.com/paper/1612.07119/) (2016)
- [Neuromorphic Silicon Photonic Networks](https://mlsanity.com/paper/1611.02272/) (2016)
- [NullHop: A Flexible Convolutional Neural Network Accelerator Based on Sparse Representations of Feature Maps](https://mlsanity.com/paper/1706.01406/) (2017)
- [A Survey on Silicon Photonics for Deep Learning](https://mlsanity.com/paper/2101.01751/) (2021)
- [Digital Electronics and Analog Photonics for Convolutional Neural Networks (DEAP-CNNs)](https://mlsanity.com/paper/1907.01525/) (2019)

## Built on by (most cited first, 15 of 15)

- [RecLight: A Recurrent Neural Network Accelerator with Integrated Silicon Photonics](https://mlsanity.com/paper/2209.00084/) (2022)
- [SONIC: A Sparse Neural Network Inference Accelerator with Silicon Photonics for Energy-Efficient Deep Learning](https://mlsanity.com/paper/2109.04459/) (2021)
- [A Silicon Photonic Accelerator for Convolutional Neural Networks with Heterogeneous Quantization](https://mlsanity.com/paper/2205.11244/) (2022)
- [GHOST: A Graph Neural Network Accelerator using Silicon Photonics](https://mlsanity.com/paper/2307.01782/) (2023)
- [Machine Learning Accelerators in 2.5D Chiplet Platforms with Silicon Photonics](https://mlsanity.com/paper/2301.12252/) (2023)
- [SafeLight: Enhancing Security in Optical Convolutional Neural Network Accelerators](https://mlsanity.com/paper/2411.16712/) (2024)
- [An Optical XNOR-Bitcount Based Accelerator for Efficient Inference of Binary Neural Networks](https://mlsanity.com/paper/2302.06405/) (2023)
- [Cross-Layer Design for AI Acceleration with Non-Coherent Optical Computing](https://mlsanity.com/paper/2303.12910/) (2023)
- [High-Speed and Energy-Efficient Non-Binary Computing with Polymorphic Electro-Optic Circuits and Architectures](https://mlsanity.com/paper/2304.07608/) (2023)
- [Accelerating Neural Networks for Large Language Models and Graph Processing with Silicon Photonics](https://mlsanity.com/paper/2401.06885/) (2024)
- [OPIMA: Optical Processing-In-Memory for Convolutional Neural Network Acceleration](https://mlsanity.com/paper/2407.08205/) (2024)
- [A Comparative Analysis of Microrings Based Incoherent Photonic GEMM Accelerators](https://mlsanity.com/paper/2402.03149/) (2024)
- [Optical Computing for Deep Neural Network Acceleration: Foundations, Recent Developments, and Emerging Directions](https://mlsanity.com/paper/2407.21184/) (2024)
- [Towards Experience Replay for Class-Incremental Learning in Fully-Binary Networks](https://mlsanity.com/paper/2503.07107/) (2025)
- [Accelerating Diffusion Models for Generative AI Applications with Silicon Photonics](https://mlsanity.com/paper/2603.07626/) (2026)

## Abstract (arXiv)

Domain specific neural network accelerators have garnered attention because of their improved energy efficiency and inference performance compared to CPUs and GPUs. Such accelerators are thus well suited for resource-constrained embedded systems. However, mapping sophisticated neural network models on these accelerators still entails significant energy and memory consumption, along with high inference time overhead. Binarized neural networks (BNNs), which utilize single-bit weights, represent an efficient way to implement and deploy neural network models on accelerators. In this paper, we present a novel optical-domain BNN accelerator, named ROBIN, which intelligently integrates heterogeneous microring resonator optical devices with complementary capabilities to efficiently implement the key functionalities in BNNs. We perform detailed fabrication-process variation analyses at the optical device level, explore efficient corrective tuning for these devices, and integrate circuit-level optimization to counter thermal variations. As a result, our proposed ROBIN architecture possesses the desirable traits of being robust, energy-efficient, low latency, and high throughput, when executing BNN models. Our analysis shows that ROBIN can outperform the best-known optical BNN accelerators and also many electronic accelerators. Specifically, our energy-efficient ROBIN design exhibits energy-per-bit values that are ~4x lower than electronic BNN accelerators and ~933x lower than a recently proposed photonic BNN accelerator, while a performance-efficient ROBIN design shows ~3x and ~25x better performance than electronic and photonic BNN accelerators, respectively.