Search Results for author: Łukasz Dudziak

Found 11 papers, 6 papers with code

Zero-Cost Proxies Meet Differentiable Architecture Search

1 code implementation12 Jun 2021 Lichuan Xiang, Łukasz Dudziak, Mohamed S. Abdelfattah, Thomas Chau, Nicholas D. Lane, Hongkai Wen

Differentiable neural architecture search (NAS) has attracted significant attention in recent years due to its ability to quickly discover promising architectures of deep neural networks even in very large search spaces.

Neural Architecture Search

Zero-Cost Proxies for Lightweight NAS

2 code implementations ICLR 2021 Mohamed S. Abdelfattah, Abhinav Mehrotra, Łukasz Dudziak, Nicholas D. Lane

For example, Spearman's rank correlation coefficient between final validation accuracy and our best zero-cost proxy on NAS-Bench-201 is 0. 82, compared to 0. 61 for EcoNAS (a recently proposed reduced-training proxy).

Neural Architecture Search

$μ$NAS: Constrained Neural Architecture Search for Microcontrollers

1 code implementation27 Oct 2020 Edgar Liberis, Łukasz Dudziak, Nicholas D. Lane

IoT devices are powered by microcontroller units (MCUs) which are extremely resource-scarce: a typical MCU may have an underpowered processor and around 64 KB of memory and persistent storage, which is orders of magnitude fewer computational resources than is typically required for deep learning.

Image Classification Neural Architecture Search

BRP-NAS: Prediction-based NAS using GCNs

2 code implementations NeurIPS 2020 Łukasz Dudziak, Thomas Chau, Mohamed S. Abdelfattah, Royson Lee, Hyeji Kim, Nicholas D. Lane

What is more, we investigate prediction quality on different metrics and show that sample efficiency of the predictor-based NAS can be improved by considering binary relations of models and an iterative data selection strategy.

Neural Architecture Search

Journey Towards Tiny Perceptual Super-Resolution

1 code implementation ECCV 2020 Royson Lee, Łukasz Dudziak, Mohamed Abdelfattah, Stylianos I. Venieris, Hyeji Kim, Hongkai Wen, Nicholas D. Lane

Recent works in single-image perceptual super-resolution (SR) have demonstrated unprecedented performance in generating realistic textures by means of deep convolutional networks.

Neural Architecture Search Super-Resolution

Best of Both Worlds: AutoML Codesign of a CNN and its Hardware Accelerator

no code implementations11 Feb 2020 Mohamed S. Abdelfattah, Łukasz Dudziak, Thomas Chau, Royson Lee, Hyeji Kim, Nicholas D. Lane

We automate HW-CNN codesign using NAS by including parameters from both the CNN model and the HW accelerator, and we jointly search for the best model-accelerator pair that boosts accuracy and efficiency.

General Classification Image Classification +2

MobiSR: Efficient On-Device Super-Resolution through Heterogeneous Mobile Processors

no code implementations21 Aug 2019 Royson Lee, Stylianos I. Venieris, Łukasz Dudziak, Sourav Bhattacharya, Nicholas D. Lane

In recent years, convolutional networks have demonstrated unprecedented performance in the image restoration task of super-resolution (SR).

Image Restoration Model Compression +1

ShrinkML: End-to-End ASR Model Compression Using Reinforcement Learning

no code implementations8 Jul 2019 Łukasz Dudziak, Mohamed S. Abdelfattah, Ravichander Vipperla, Stefanos Laskaridis, Nicholas D. Lane

Our results show that in the absence of retraining our RL-based search is an effective and practical method to compress a production-grade ASR system.

automatic-speech-recognition AutoML +4

Dynamic Channel Pruning: Feature Boosting and Suppression

2 code implementations ICLR 2019 Xitong Gao, Yiren Zhao, Łukasz Dudziak, Robert Mullins, Cheng-Zhong Xu

Making deep convolutional neural networks more accurate typically comes at the cost of increased computational and memory resources.

Model Compression Network Pruning

Cannot find the paper you are looking for? You can Submit a new open access paper.