Multiagent Reinforcement Learning for Hyperparameter Optimization of Convolutional Neural Networks

Nowadays, deep convolutional neural networks (DCNNs) play a significant role in many application domains, such as computer vision, medical imaging, and image processing. Nonetheless, designing a DCNN, able to defeat the state of the art, is a manual, challenging, and time-consuming task, due to the...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:IEEE transactions on computer-aided design of integrated circuits and systems Ročník 41; číslo 4; s. 1034 - 1047
Hlavní autoři: Iranfar, Arman, Zapater, Marina, Atienza, David
Médium: Journal Article
Jazyk:angličtina
Vydáno: New York IEEE 01.04.2022
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Témata:
Accuracy
Artificial neural networks
Computer architecture
Computer vision
Convolution
Convolutional neural network (CNN)
hyperparameter optimization
Image classification
Image processing
Image segmentation
Kernel
Learning
Medical imaging
Multiagent systems
neural architecture search (NAS)
Neural networks
Optimization
Reinforcement learning
reinforcement Learning (RL)
Search problems
Subspaces
Training
ISSN:0278-0070, 1937-4151
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Nowadays, deep convolutional neural networks (DCNNs) play a significant role in many application domains, such as computer vision, medical imaging, and image processing. Nonetheless, designing a DCNN, able to defeat the state of the art, is a manual, challenging, and time-consuming task, due to the extremely large design space, as a consequence of a large number of layers and their corresponding hyperparameters. In this work, we address the challenge of performing hyperparameter optimization of DCNNs through a novel multiagent reinforcement learning (MARL)-based approach, eliminating the human effort. In particular, we adapt <inline-formula> <tex-math notation="LaTeX">Q </tex-math></inline-formula>-learning and define learning agents per layer to split the design space into independent smaller design subspaces such that each agent fine tunes the hyperparameters of the assigned layer concerning a global reward. Moreover, we provide a novel formation of <inline-formula> <tex-math notation="LaTeX">Q </tex-math></inline-formula>-tables along with a new update rule that facilitates agents' communication. Our MARL-based approach is data driven and able to consider an arbitrary set of design objectives and constraints. We apply our MARL-based solution to different well-known DCNNs, including GoogLeNet, VGG, and U-Net, and various datasets for image classification and semantic segmentation. Our results have shown that compared to the original CNNs, the MARL-based approach can reduce the model size, training time, and inference time by up to, respectively, <inline-formula> <tex-math notation="LaTeX">83\times </tex-math></inline-formula>, 52%, and 54% without any degradation in accuracy. Moreover, our approach is very competitive to state-of-the-art neural architecture search methods in terms of the designed CNN accuracy and its number of parameters while significantly reducing the optimization cost.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0278-0070
1937-4151
DOI:10.1109/TCAD.2021.3077193