paper-with-me

홈 › Papers

MANAS: Multi-Agent Neural Architecture Search

2019-09-03 · Vasco Lopes, Fabio Maria Carlucci, Pedro M Esperança, Marco Singh, Victor Gabillon, Antoine Yang, Hang Xu, Zewei Chen, Jun Wang

The Neural Architecture Search (NAS) problem is typically formulated as a graph search problem where the goal is to learn the optimal operations over edges in order to maximise a graph-level global objective. Due to the large architecture parameter space, efficiency is a key bottleneck preventing NAS from its practical use. In this paper, we address the issue by framing NAS as a multi-agent problem where agents control a subset of the network and coordinate to reach optimal architectures. We provide two distinct lightweight implementations, with reduced memory requirements (1/8th of state-of-the-art), and performances above those of much more computationally expensive methods. Theoretically, we demonstrate vanishing regrets of the form O(sqrt(T)), with T being the total number of rounds. Finally, aware that random search is an, often ignored, effective baseline we perform additional experiments on 3 alternative datasets and 2 network configurations, and achieve favourable results in comparison.

📄 PDF Abstract BibTeX arXiv:1909.01051

Code (0)

등록된 구현이 없습니다.

Tasks

Neural Architecture Search

Methods 이 논문이 사용한 방법론

Random Search Random Search replaces the exhaustive enumeration of all combinations by selecting them randomly. This can be simply applied to the discrete setting described above, but also…
Sigmoid Activation 설명 없음
Tanh Activation 설명 없음
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
LSTM An LSTM is a type of recurrent neural network that addresses the vanishing gradient problem in vanilla…

Similar Papers 제목 키워드 기반

MANAS: Multi-Scale and Multi-Level Neural Architecture Search for Low-Dose CT Denoising

2021-03-24 · Zexin Lu, Wenjun Xia, Yongqiang Huang, Hongming Shan 외

Lowering the radiation dose in computed tomography (CT) can greatly reduce the potential risk to public health. However, the reconstructed images from the dose-reduced CT or low-dose CT (LDCT) suffer from severe noise, c…

Computed Tomography (CT)DenoisingNeural Architecture Search

Learn Basic Skills and Reuse: Modularized Adaptive Neural Architecture Search (MANAS)

2022-08-23 · Hanxiong Chen, Yunqi Li, He Zhu, Yongfeng Zhang

Human intelligence is able to first learn some basic skills for solving basic problems and then assemble such basic skills into complex skills for solving complex or new problems. For example, the basic skills "dig hole,…

Neural Architecture Search

Neural Architecture Search using Covariance Matrix Adaptation Evolution Strategy

2021-07-15 · Nilotpal Sinha, Kuan-Wen Chen

Evolution-based neural architecture search requires high computational resources, resulting in long search time. In this work, we propose a framework of applying the Covariance Matrix Adaptation Evolution Strategy (CMA-E…

GPUNeural Architecture Search

Multi-scale Attentive Image De-raining Networks via Neural Architecture Search

2022-07-02 · Lei Cai, Yuli Fu, Wanliang Huo, Youjun Xiang 외

Multi-scale architectures and attention modules have shown effectiveness in many deep learning-based image de-raining methods. However, manually designing and integrating these two components into a neural network requir…

Neural Architecture SearchRain Removal

Manas: Mining Software Repositories to Assist AutoML

2021-12-06 · Giang Nguyen, Md Johir Islam, Rangeet Pan, Hridesh Rajan

Today deep learning is widely used for building software. A software engineering problem with deep learning is that finding an appropriate convolutional neural network (CNN) model for the task can be a challenge for deve…

AutoMLGPUimage-classificationImage Classification+1