NDLI: GenSynth: a generative synthesis approach to learning generative machines for generate efficient neural networks

Content Provider	IET Digital Library
Author	Wong, Alexander Shafiee, Mohammad Javad Chwyl, Brendan Li, Francis
Abstract	The tremendous potential exhibited by deep learning is often offset by architectural and computational complexity, making widespread deployment a challenge for edge scenarios such as mobile and other consumer devices. To tackle this challenge, we explore the following idea: Can we learn generative machines to automatically generate deep neural networks with efficient network architectures? In this study, we introduce the idea of generative synthesis, which is premised on the intricate interplay between a generator-inquisitor pair that work in tandem to garner insights and learn to generate highly efficient deep neural networks that best satisfies operational requirements. Experimental results for image classification, semantic segmentation, and object detection tasks illustrate the efficacy of generative synthesis (GenSynth) in producing generators that automatically generate highly efficient deep neural networks (which we nickname FermiNets with higher model efficiency and lower computational costs (reaching > 10 × more efficient and fewer multiply-accumulate operations than several tested state-of-the-art networks), as well as higher energy efficiency (reaching > 4 × improvements in image inferences per joule consumed on a Nvidia Tegra X2 mobile processor). As such, GenSynth can be a powerful, generalised approach for accelerating and improving the building of deep neural networks for on-device edge scenarios.
Starting Page	986
Ending Page	989
Page Count	4
ISSN	00135194
Volume Number	55
e-ISSN	1350911X
Issue Number	Issue 18, Sep (2019)
Alternate Webpage(s)	https://digital-library.theiet.org/content/journals/el/55/18
Alternate Webpage(s)	https://digital-library.theiet.org/content/journals/10.1049/el.2019.1719
Journal	Electronics Letters
Publisher Date	2019-08-02
Access Restriction	Open
Rights Holder	© The Institution of Engineering and Technology
Subject Keyword	Architectural Complexity Computational Complexity Computer Vision And Image Processing Technique Consumer Device Deep Learning Efficient Network Architectures Efficient Neural Network Generative Machine Generative Synthesis Approach Generator-inquisitor Pair GenSynth Higher Energy Efficiency Higher Model Efficiency Image Classification Knowledge Engineering Technique Learning in AI Neural Computing Technique Neural Nets Object Detection Operational Requirements Optical, Image And Video Signal Processing Tested State-of-the-art Network Unique Highly Efficient Deep Neural Network
Content Type	Text
Resource Type	Article
Subject	Electrical and Electronic Engineering

Sl.	Authority	Responsibilities	Communication Details
1	Ministry of Education (GoI), Department of Higher Education	Sanctioning Authority	https://www.education.gov.in/ict-initiatives
2	Indian Institute of Technology Kharagpur	Host Institute of the Project: The host institute of the project is responsible for providing infrastructure support and hosting the project	https://www.iitkgp.ac.in
3	National Digital Library of India Office, Indian Institute of Technology Kharagpur	The administrative and infrastructural headquarters of the project	Dr. B. Sutradhar bsutra@ndl.gov.in
4	Project PI / Joint PI	Principal Investigator and Joint Principal Investigators of the project	Dr. B. Sutradhar bsutra@ndl.gov.in Prof. Saswat Chakrabarti will be added soon
5	Website/Portal (Helpdesk)	Queries regarding NDLI and its services	support@ndl.gov.in
6	Contents and Copyright Issues	Queries related to content curation and copyright issues	content@ndl.gov.in
7	National Digital Library of India Club (NDLI Club)	Queries related to NDLI Club formation, support, user awareness program, seminar/symposium, collaboration, social media, promotion, and outreach	clubsupport@ndl.gov.in
8	Digital Preservation Centre (DPC)	Assistance with digitizing and archiving copyright-free printed books	dpc@ndl.gov.in
9	IDR Setup or Support	Queries related to establishment and support of Institutional Digital Repository (IDR) and IDR workshops	idr@ndl.gov.in

Enhanced CNN for image denoising

Efficient generative model for motion deblurring

Multimodal deep network learning-based image annotation

Deep Hashing Based on VAE-GAN for Efficient Similarity Retrieval

Compressing deep-quaternion neural networks with targeted regularisation

Deep learning approach to generate offline handwritten signatures based on online samples

Efficient deep convolutional neural networks using CReLU for ATR with limited SAR images

Cooperation: A new force for boosting generative adversarial nets with dual-network structure

EXplainable AI (XAI) approach to image captioning

GenSynth: a generative synthesis approach to learning generative machines for generate efficient neural networks

Similar Documents

Enhanced CNN for image denoising

Efficient generative model for motion deblurring

Multimodal deep network learning-based image annotation

Deep Hashing Based on VAE-GAN for Efficient Similarity Retrieval

Compressing deep-quaternion neural networks with targeted regularisation

Deep learning approach to generate offline handwritten signatures based on online samples

Efficient deep convolutional neural networks using CReLU for ATR with limited SAR images

Cooperation: A new force for boosting generative adversarial nets with dual-network structure

EXplainable AI (XAI) approach to image captioning

GenSynth: a generative synthesis approach to learning generative machines for generate efficient neural networks