NDLI: Deep neural network with FGL for small dataset classification

Content Provider	IET Digital Library
Author	Guo, Chunsheng Li, Ruizhe Yang, Meng Tang, Xianghong
Abstract	In certain applications, classification models have to be trained with small datasets. This study proposes a new deep neural network with a feature generalisation layer (FGL). First, instead of using a generative network for data augmentation, the FGL is modelled using a latent variable model to diversify features directly by sharing other layers. Then, dual-objective functions are defined to optimise the parameters of the network: one minimises the generation error and the other minimises the classification error. Finally, a parallel multibranch structure is used in the FGL to improve the convergence of model training. The classification accuracy obtained using various quantities of training samples increased up to 4.63% on the MNIST dataset, up to 3.00% on the CIFAR10 nature image dataset, over the reference model. These experimental results illustrate the effectiveness of the authors’ method for training classification models with small datasets.
Starting Page	491
Ending Page	497
Page Count	7
ISSN	17519659
Volume Number	13
e-ISSN	17519667
Issue Number	Issue 3, Feb (2019)
Alternate Webpage(s)	https://digital-library.theiet.org/content/journals/iet-ipr/13/3
Alternate Webpage(s)	https://digital-library.theiet.org/content/journals/10.1049/iet-ipr.2018.5616
Journal	IET Image Processing
Publisher Date	2018-11-22
Access Restriction	Open
Rights Holder	© The Institution of Engineering and Technology
Subject Keyword	CIFAR10 Nature Image Dataset Classification Accuracy Classification Error Classification Model Data Augmentation Data Handling Technique Dataset Classification Deep Neural Network Dual-objective Function Feature Generalisation Layer FGL Generative Network Knowledge Engineering Technique Latent Variable Model Learning in AI MNIST Dataset Neural Computing Technique Neural Nets Pattern Classification Reference Model Training Sample
Content Type	Text
Resource Type	Article
Subject	Signal Processing Electrical and Electronic Engineering Computer Vision and Pattern Recognition Software

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

Learning deep discriminative features based on cosine loss function

Multi-sample inference network

Radar data simulation using deep generative networks

Music genre classification and music recommendation by using deep learning

Improving active learning by data balance to reduce annotation efforts

RAPIDO: a rejuvenating adaptive PID-type optimiser for deep neural networks

DropConnect Regularization Method with Sparsity Constraint for Neural Networks

Semi-supervised convolutional generative adversarial network for hyperspectral image classification

Multi-model deep learning approach for collaborative filtering recommendation system

Deep neural network with FGL for small dataset classification

Similar Documents

Learning deep discriminative features based on cosine loss function

Multi-sample inference network

Radar data simulation using deep generative networks

Music genre classification and music recommendation by using deep learning

Improving active learning by data balance to reduce annotation efforts

RAPIDO: a rejuvenating adaptive PID-type optimiser for deep neural networks

DropConnect Regularization Method with Sparsity Constraint for Neural Networks

Semi-supervised convolutional generative adversarial network for hyperspectral image classification

Multi-model deep learning approach for collaborative filtering recommendation system

Deep neural network with FGL for small dataset classification