Machine learning for microcontroller-class hardware: A review

SS Saha, SS Sandha, M Srivastava - IEEE Sensors Journal, 2022 - ieeexplore.ieee.org
The advancements in machine learning (ML) opened a new opportunity to bring intelligence
to the low-end Internet-of-Things (IoT) nodes, such as microcontrollers. Conventional ML …

A review of neural architecture search

D Baymurzina, E Golikov, M Burtsev - Neurocomputing, 2022 - Elsevier
Despite the impressive progress in neural network architecture design, improving the
performance of the existing state-of-the-art models has become increasingly challenging …

Deep model reassembly

X Yang, D Zhou, S Liu, J Ye… - Advances in neural …, 2022 - proceedings.neurips.cc
In this paper, we explore a novel knowledge-transfer task, termed as Deep Model
Reassembly (DeRy), for general-purpose model reuse. Given a collection of heterogeneous …

Zero-cost proxies for lightweight nas

MS Abdelfattah, A Mehrotra, Ł Dudziak… - arXiv preprint arXiv …, 2021 - arxiv.org
Neural Architecture Search (NAS) is quickly becoming the standard methodology to design
neural network models. However, NAS is typically compute-intensive because multiple …

Neural architecture search on imagenet in four gpu hours: A theoretically inspired perspective

W Chen, X Gong, Z Wang - arXiv preprint arXiv:2102.11535, 2021 - arxiv.org
Neural Architecture Search (NAS) has been explosively studied to automate the discovery of
top-performer neural networks. Current works require heavy training of supernet or intensive …

Brp-nas: Prediction-based nas using gcns

L Dudziak, T Chau, M Abdelfattah… - Advances in …, 2020 - proceedings.neurips.cc
Neural architecture search (NAS) enables researchers to automatically explore broad
design spaces in order to improve efficiency of neural networks. This efficiency is especially …

Bananas: Bayesian optimization with neural architectures for neural architecture search

C White, W Neiswanger, Y Savani - … of the AAAI conference on artificial …, 2021 - ojs.aaai.org
Over the past half-decade, many methods have been considered for neural architecture
search (NAS). Bayesian optimization (BO), which has long had success in hyperparameter …

[PDF][PDF] Nas-bench-301 and the case for surrogate benchmarks for neural architecture search

J Siems, L Zimmer, A Zela, J Lukasik… - arXiv preprint arXiv …, 2020 - researchgate.net
ABSTRACT Neural Architecture Search (NAS) is a logical next step in the automatic learning
of representations, but the development of NAS methods is slowed by high computational …

Zen-nas: A zero-shot nas for high-performance image recognition

M Lin, P Wang, Z Sun, H Chen, X Sun… - Proceedings of the …, 2021 - openaccess.thecvf.com
Accuracy predictor is a key component in Neural Architecture Search (NAS) for ranking
architectures. Building a high-quality accuracy predictor usually costs enormous …

How powerful are performance predictors in neural architecture search?

C White, A Zela, R Ru, Y Liu… - Advances in Neural …, 2021 - proceedings.neurips.cc
Early methods in the rapidly developing field of neural architecture search (NAS) required
fully training thousands of neural networks. To reduce this extreme computational cost …