English
Related papers

Related papers: Learning Where To Look -- Generative NAS is Surpri…

200 papers

Energy consumption from the selection, training, and deployment of deep learning models has seen a significant uptick recently. This work aims to facilitate the design of energy-efficient deep learning models that require less computational…

Machine Learning · Computer Science 2024-03-25 Pedram Bakhtiarifard , Christian Igel , Raghavendra Selvan

Recent Neural Architecture Search (NAS) solutions have produced impressive results training super-networks and then deriving subnetworks, a.k.a. child models that outperform expert-crafted models from a pre-defined search space. Efficient…

Machine Learning · Computer Science 2021-12-22 J. Pablo Muñoz , Nikolay Lyalyushkin , Yash Akhauri , Anastasia Senina , Alexander Kozlov , Nilesh Jain

Neural Architecture Search (NAS), i.e., the automation of neural network design, has gained much popularity in recent years with increasingly complex search algorithms being proposed. Yet, solid comparisons with simple baselines are often…

Neural and Evolutionary Computing · Computer Science 2020-07-28 T. Den Ottelander , A. Dushatskiy , M. Virgolin , P. A. N. Bosman

Neural architecture search (NAS) is a hot topic in the field of automated machine learning and outperforms humans in designing neural architectures on quite a few machine learning tasks. Motivated by the natural representation form of…

Neural and Evolutionary Computing · Computer Science 2021-09-30 Xuan Wu , Linhan Jia , Xiuyi Zhang , Liang Chen , Yanchun Liang , You Zhou , Chunguo Wu

In the recent past, the success of Neural Architecture Search (NAS) has enabled researchers to broadly explore the design space using learning-based methods. Apart from finding better neural network architectures, the idea of automation has…

Machine Learning · Computer Science 2019-11-04 Qing Lu , Weiwen Jiang , Xiaowei Xu , Yiyu Shi , Jingtong Hu

Layout designs are encountered in a variety of fields. For problems with many design degrees of freedom, efficiency of design methods becomes a major concern. In recent years, machine learning methods such as artificial neural networks have…

Machine Learning · Computer Science 2021-02-01 Chao Qian , Renkai Tan , Wenjing Ye

The standard paradigm in Neural Architecture Search (NAS) is to search for a fully deterministic architecture with specific operations and connections. In this work, we instead propose to search for the optimal operation distribution, thus…

Machine Learning · Computer Science 2021-11-09 Xingchen Wan , Binxin Ru , Pedro M. Esperança , Fabio M. Carlucci

Convolutional neural network (CNN) architectures have traditionally been explored by human experts in a manual search process that is time-consuming and ineffectively explores the massive space of potential solutions. Neural architecture…

Neural and Evolutionary Computing · Computer Science 2019-04-02 Gerard Jacques van Wyk , Anna Sergeevna Bosman

An important step in the task of neural network design, such as hyper-parameter optimization (HPO) or neural architecture search (NAS), is the evaluation of a candidate model's performance. Given fixed computational resources, one can…

Machine Learning · Computer Science 2021-03-09 Shengcao Cao , Xiaofang Wang , Kris Kitani

Search space design is very critical to neural architecture search (NAS) algorithms. We propose a fine-grained search space comprised of atomic blocks, a minimal search unit that is much smaller than the ones used in recent NAS algorithms.…

Computer Vision and Pattern Recognition · Computer Science 2020-02-25 Jieru Mei , Yingwei Li , Xiaochen Lian , Xiaojie Jin , Linjie Yang , Alan Yuille , Jianchao Yang

The design of handcrafted neural networks requires a lot of time and resources. Recent techniques in Neural Architecture Search (NAS) have proven to be competitive or better than traditional handcrafted design, although they require domain…

Machine Learning · Computer Science 2021-03-17 Cat P. Le , Mohammadreza Soltani , Robert Ravier , Vahid Tarokh

Neural Architecture Search (NAS) represents a class of methods to generate the optimal neural network architecture and typically iterate over candidate architectures till convergence over some particular metric like validation loss. They…

Machine Learning · Computer Science 2019-10-22 Abhishek Singh , Anubhav Garg , Jinan Zhou , Shiv Ram Dubey , Debo Dutta

Neural Architecture Search (NAS) methods have been successfully applied to image tasks with excellent results. However, NAS methods are often complex and tend to converge to local minima as soon as generated architectures seem to yield good…

Machine Learning · Computer Science 2021-10-29 Vasco Lopes , Miguel Santos , Bruno Degardin , Luís A. Alexandre

Automatic methods for generating state-of-the-art neural network architectures without human experts have generated significant attention recently. This is because of the potential to remove human experts from the design loop which can…

Machine Learning · Computer Science 2019-11-22 George Adam , Jonathan Lorraine

Performing analytical tasks over graph data has become increasingly interesting due to the ubiquity and large availability of relational information. However, unlike images or sentences, there is no notion of sequence in networks. Nodes…

Neural and Evolutionary Computing · Computer Science 2020-10-28 Matheus Nunes , Gisele L. Pappa

We propose a novel strategy for Neural Architecture Search (NAS) based on Bregman iterations. Starting from a sparse neural network our gradient-based one-shot algorithm gradually adds relevant parameters in an inverse scale space manner.…

Machine Learning · Computer Science 2021-06-07 Leon Bungert , Tim Roith , Daniel Tenbrinck , Martin Burger

Developing effective surrogates (performance predictors) for Neural Architecture Search (NAS) typically requires expensive fine-tuning or the engineering of complex representations. We propose a low-cost embedding strategy that leverages…

Machine Learning · Computer Science 2026-05-18 Pranav Somu , Advay Balakrishnan , Stepan Kravtsov , Aaron McDaniel , Jason Zutty

Resource is an important constraint when deploying Deep Neural Networks (DNNs) on mobile and edge devices. Existing works commonly adopt the cell-based search approach, which limits the flexibility of network patterns in learned cell…

Machine Learning · Computer Science 2020-03-04 Tunhou Zhang , Hsin-Pai Cheng , Zhenwen Li , Feng Yan , Chengyu Huang , Hai Li , Yiran Chen

The use of automatic methods, often referred to as Neural Architecture Search (NAS), in designing neural network architectures has recently drawn considerable attention. In this work, we present an efficient NAS approach, named HM- NAS,…

Machine Learning · Computer Science 2019-09-10 Shen Yan , Biyi Fang , Faen Zhang , Yu Zheng , Xiao Zeng , Hui Xu , Mi Zhang

Neural architecture search has attracted wide attentions in both academia and industry. To accelerate it, researchers proposed weight-sharing methods which first train a super-network to reuse computation among different operators, from…

Machine Learning · Computer Science 2020-12-16 Xin Chen , Lingxi Xie , Jun Wu , Longhui Wei , Yuhui Xu , Qi Tian