Journal Article10.1007/s12652-022-04025-2
Localization and reduction of redundancy in CNN using L1-sparsity induction
17
TL;DR: This paper proposes a new optimization model for localizing and removing the redundancy in CNN, and uses the evolutionary genetic algorithm to solve the proposed model generating finally an optimal CNN with prior information about the redundancy distribution.
read more
About: This article is published in Journal of Ambient Intelligence and Humanized Computing. The article was published on 20 Jun 2022. The article focuses on the topics: Redundancy (engineering) & Computer science.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
A deep learning framework for time series classification using normal cloud representation and convolutional neural network optimization
TL;DR: In this article , an optimized deep learning framework for time series classification using normal cloud representation and convolutional neural networks optimization (NCR•CNNO) is proposed, which consists of two phases: in the first one, they convert the raw time series to a matrix of characteristics using two-dimensional normal cloud representations.
18
A Multi-objective Optimization Model for Redundancy Reduction in Convolutional Neural Networks
TL;DR: A new multi-objective optimization model for redundancy reduction in CNNs named MoRR-CNN allows to eliminate the unwanted parameters (kernels and weights) as well as to speeding up the CNN evaluation process.
9
Ensuring the privacy and security of IoT-medical data: a hybrid deep learning-based encryption and blockchain-enabled transmission
Aditya Kaushal Ranjan,Prabhat Kumar +1 more
6
Heterogeneous transfer learning: recent developments, applications, and challenges
Siraj Khan,Pengshuai Yin,Yuxin Guo,Muhammad Asim,Ahmed A. Abd El-Latif +4 more
5
Healthcare entity recognition based on deep learning
Qinlu He,Pengze Gao,Fan Zhang,Genqing Bian,Zhen Li,Zan Wang +5 more
- 23 Sep 2023
3
References
Recent advances in convolutional neural network acceleration
TL;DR: In this paper, the authors present a taxonomy of CNN acceleration methods in terms of three levels, i.e. structure level, algorithm level, and implementation level, for CNN architectures compression, algorithm optimization and hardware-based improvement.
389
Particle swarm optimization of deep neural networks architectures for image classification
TL;DR: A novel algorithm based on particle swarm optimization (PSO), capable of fast convergence when compared with others evolutionary approaches, to automatically search for meaningful deep convolutional neural networks (CNNs) architectures for image classification tasks, named psoCNN.
369
Artificial neural network for modeling nitrate pollution of groundwater in marginal area of Zayandeh-rood River, Isfahan, Iran
TL;DR: In this article, the authors used MATLAB software and three-layer perceptron network for modeling and estimation of nitrate pollution in groundwater of marginal area of Zayandeh-rood River, Isfahan, Iran, using water quality and artificial neural networks.
359
A deep learning framework for building energy consumption forecast
TL;DR: It is observed that the accurate energy demand forecast provided by k CNN-LSTM due to its ability to learn the spatio-temporal dependencies in the energy consumption data makes it a suitable deep learning model for energy consumption forecast problems.
333
Application of deep learning to cybersecurity: A survey
TL;DR: This survey focuses on recent DL approaches that have been proposed in the area of cybersecurity, namely intrusion detection, malware detection, phishing/spam detection, and website defacement detection.
294