Computational Intelligence and Neuroscience

Compression of Deep Learning Models for Resource-Constrained Devices


Publishing date
01 Mar 2022
Status
Closed
Submission deadline
05 Nov 2021

1Bennett University, Greater Noida, India

2Brunel University London, London, UK

This issue is now closed for submissions.
More articles will be published in the near future.

Compression of Deep Learning Models for Resource-Constrained Devices

This issue is now closed for submissions.
More articles will be published in the near future.

Description

In recent years, deep learning has become popular in research due to its applicability in many industries. For instance, deep learning can be applied in healthcare, security surveillance, self-drive car, human activity recognition, recommended systems, image quality enhancement, transportation, prediction, forecasting, etc. Before the introduction of deep learning, prediction and decision-making can be achieved using statistical methods and machine learning. Deep learning algorithms have been solving successfully complex real-time problems. This was previously not possible with machine learning and computer vision methods.

Deep learning has also gained popularity because it automatically extracts the important features from training data and these features help to make an appropriate decision. However, there are challenges in deep learning such as problems of high computation power and resources. Moreover, deep learning models are computationally extensive and require high storage space. Therefore, a deep learning model is not well suited for edge devices. Users are not able to get high computation resources in a real-time domain from a remote location or in the case of mobility. Hence, these deep learning models require significant improvement. For instance, there is a need to make deep learning models that include lightweight and better inference time so that the models can be compatible with resource-constrained devices. Recent research has shown significant improvement in compression techniques by applying pruning, lossy weight encoding, parameter sharing, multilayer pruning, low-rank factorization, etc. To compress deep learning models, two approaches exist: compression during training and compression of the trained model. Moreover, various techniques are available for model optimization and compression for resource-constrained devices. For instance, genetic algorithms, swarm optimization, swarm intelligence, nature-inspired optimization, game-theoretic approach, chemical reaction optimization, and differential evolution.

The aim of the Special Issue is to bring together original research and review articles discussing the compression of deep learning models for resource-constrained devices. We welcome submissions from researchers who have been working on the development and deployment of deep learning models in edge devices (e.g., Raspberry Pi, Google edge tensor processing unit (Google TPU), NVIDIA Jetson Nano Developer Kit, Android devices, etc). This Special Issue invites original research discussing innovative architectures and training methods for effective and efficient compression.

Potential topics include but are not limited to the following:

  • Model optimization and compression for medical applications
  • Model optimization and compression for Internet of Things (IoT) and edge applications
  • Model optimization and compression for deep learning algorithms in security analysis applications
  • New architectures for model compression include pruning, quantization, knowledge distillation, neural architecture search (NAS), etc.
  • Generalize lightweight architectures for deep learning problems
  • Compression approaches for deep reinforcement learning
  • Efficient use of computation resources for executing deep learning models
  • Architectures and models that work with less training data on remote applications
  • Compressed deep learning model for explainable artificial intelligence
  • Compressed and accelerated versions of famous pr-trained architectures (e.g., AlexNet, OxfordNet (VGG16), residual neural network (ResNet), etc.)
  • Compression and acceleration of object detection model such as "You Only Look Once" (YOLO) model, and single-shot detector (SSD)
  • Accelerate the UNet and VNet architectures
  • Methodology and framework for developing storage constraints in deep learning models

Articles

  • Special Issue
  • - Volume 2022
  • - Article ID 2995205
  • - Research Article

Feature Extraction of Athlete’s Post-Match Psychological and Emotional Changes Based on Deep Learning

Shuchang Zhang | Fengjun Shan
  • Special Issue
  • - Volume 2022
  • - Article ID 9485933
  • - Research Article

A Post-training Quantization Method for the Design of Fixed-Point-Based FPGA/ASIC Hardware Accelerators for LSTM/GRU Algorithms

Emilio Rapuano | Tommaso Pacini | Luca Fanucci
  • Special Issue
  • - Volume 2022
  • - Article ID 7653766
  • - Research Article

Online Course Model of Social and Political Education Using Deep Learning

Min Zhang | Qiong Gao
  • Special Issue
  • - Volume 2022
  • - Article ID 9933929
  • - Research Article

Legal Text Recognition Using LSTM-CRF Deep Learning Model

Hesheng Xu | Bin Hu
  • Special Issue
  • - Volume 2022
  • - Article ID 1503188
  • - Research Article

Real-Time Gender Recognition for Juvenile and Adult Faces

Sandeep Kumar Gupta | Seid Hassen Yesuf | Neeta Nain
  • Special Issue
  • - Volume 2022
  • - Article ID 9638438
  • - Research Article

Medical Image Captioning Using Optimized Deep Learning Model

Arjun Singh | Jaya Krishna Raguru | ... | Mohammad Aman Ullah
  • Special Issue
  • - Volume 2022
  • - Article ID 6711331
  • - Research Article

Application of Unsupervised Migration Method Based on Deep Learning Model in Basketball Training

Hui Sun | Yu Wang | Yujue Wang
  • Special Issue
  • - Volume 2022
  • - Article ID 2213273
  • - Research Article

DeepCompNet: A Novel Neural Net Model Compression Architecture

M. Mary Shanthi Rani | P. Chitra | ... | S. Nithya
  • Special Issue
  • - Volume 2022
  • - Article ID 9580896
  • - Research Article

Significance of Visible Non-Invasive Risk Attributes for the Initial Prediction of Heart Disease Using Different Machine Learning Techniques

Syed Immamul Ansarullah | Syed Mohsin Saif | ... | Mudasir Manzoor Kirmani
  • Special Issue
  • - Volume 2022
  • - Article ID 4806763
  • - Research Article

Application of the PBL Model Based on Deep Learning in Physical Education Classroom Integrating Production and Education

Honghai Li | Hongtao Deng | Yi Zhang
Computational Intelligence and Neuroscience
 Journal metrics
See full report
Acceptance rate51%
Submission to final decision41 days
Acceptance to publication25 days
CiteScore3.900
Journal Citation Indicator0.700
Impact Factor3.120
 Submit

Article of the Year Award: Outstanding research contributions of 2021, as selected by our Chief Editors. Read the winning articles.