# Accelerator-aware Neural Network Design using AutoML

arXiv: https://arxiv.org/abs/2003.02838 · HTML: https://mlsanity.com/paper/2003.02838/

## Key facts

- Cited by 30 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Mar 2020.

## Built on by (most cited first, 30 of 30)

- [EfficientNetV2: Smaller Models and Faster Training](https://mlsanity.com/paper/2104.00298/) (2021)
- [A Comprehensive Survey on Hardware-Aware Neural Architecture Search](https://mlsanity.com/paper/2101.09336/) (2021)
- [Making AI Less "Thirsty": Uncovering and Addressing the Secret Water Footprint of AI Models](https://mlsanity.com/paper/2304.03271/) (2023)
- [Lightweight Deep Learning for Resource-Constrained Environments: A Survey](https://mlsanity.com/paper/2404.07236/) (2024)
- [Data-Driven Offline Optimization For Architecting Hardware Accelerators](https://mlsanity.com/paper/2110.11346/) (2021)
- [Apollo: Transferable Architecture Exploration](https://mlsanity.com/paper/2102.01723/) (2021)
- [Rethinking Co-design of Neural Architectures and Hardware Accelerators](https://mlsanity.com/paper/2102.08619/) (2021)
- [Towards Environmentally Equitable AI via Geographical Load Balancing](https://mlsanity.com/paper/2307.05494/) (2023)
- [CAFE: Carbon-Aware Federated Learning in Geographically Distributed Data Centers](https://mlsanity.com/paper/2311.03615/) (2023)
- [Searching for Efficient Neural Architectures for On-Device ML on Edge TPUs](https://mlsanity.com/paper/2204.14007/) (2022)
- [QAPPA: Quantization-Aware Power, Performance, and Area Modeling of DNN Accelerators](https://mlsanity.com/paper/2205.08648/) (2022)
- [PerfSAGE: Generalized Inference Performance Predictor for Arbitrary Deep Learning Models on Edge Devices](https://mlsanity.com/paper/2301.10999/) (2023)
- [Realtime Facial Expression Recognition: Neuromorphic Hardware vs. Edge AI Accelerators](https://mlsanity.com/paper/2403.08792/) (2024)
- [Evaluating Pre-trained Convolutional Neural Networks and Foundation Models as Feature Extractors for Content-based Medical Image Retrieval](https://mlsanity.com/paper/2409.09430/) (2024)
- [Deep Learning on Edge TPUs](https://mlsanity.com/paper/2108.13732/) (2021)
- [QADAM: Quantization-Aware DNN Accelerator Modeling for Pareto-Optimality](https://mlsanity.com/paper/2205.13045/) (2022)
- [FuSeConv: Fully Separable Convolutions for Fast Inference on Systolic Arrays](https://mlsanity.com/paper/2105.13434/) (2021)
- [U-Boost NAS: Utilization-Boosted Differentiable Neural Architecture Search](https://mlsanity.com/paper/2203.12412/) (2022)
- [Revisiting Architecture-aware Knowledge Distillation: Smaller Models and Faster Search](https://mlsanity.com/paper/2206.13130/) (2022)
- [QUIDAM: A Framework for Quantization-Aware DNN Accelerator and Model Co-Exploration](https://mlsanity.com/paper/2206.15463/) (2022)
- [Design and Scaffolded Training of an Efficient DNN Operator for Computer Vision on the Edge](https://mlsanity.com/paper/2108.11441/) (2021)
- [ISyNet: Convolutional Neural Networks design for AI accelerator](https://mlsanity.com/paper/2109.01932/) (2021)
- [Hardware-aware mobile building block evaluation for computer vision](https://mlsanity.com/paper/2208.12694/) (2022)
- [SequeL: A Continual Learning Library in PyTorch and JAX](https://mlsanity.com/paper/2304.10857/) (2023)
- [Comparison between transformers and convolutional models for fine-grained classification of insects](https://mlsanity.com/paper/2307.11112/) (2023)
- [Performance of computer vision algorithms for fine-grained classification using crowdsourced insect images](https://mlsanity.com/paper/2404.03474/) (2024)
- [Tech Report: One-stage Lightweight Object Detectors](https://mlsanity.com/paper/2210.17151/) (2022)
- [Enabling Hard Constraints in Differentiable Neural Network and Accelerator Co-Exploration](https://mlsanity.com/paper/2301.09312/) (2023)
- [Accel-NASBench: Sustainable Benchmarking for Accelerator-Aware NAS](https://mlsanity.com/paper/2404.08005/) (2024)
- [Efficient Deep Learning Board: Training Feedback Is Not All You Need](https://mlsanity.com/paper/2410.14743/) (2024)

## Abstract (arXiv)

While neural network hardware accelerators provide a substantial amount of raw compute throughput, the models deployed on them must be co-designed for the underlying hardware architecture to obtain the optimal system performance. We present a class of computer vision models designed using hardware-aware neural architecture search and customized to run on the Edge TPU, Google's neural network hardware accelerator for low-power, edge devices. For the Edge TPU in Coral devices, these models enable real-time image classification performance while achieving accuracy typically seen only with larger, compute-heavy models running in data centers. On Pixel 4's Edge TPU, these models improve the accuracy-latency tradeoff over existing SoTA mobile models.