Filters








189,978 Hits in 3.8 sec

Learning Neural Network Classifiers with Low Model Complexity [article]

Jayadeva, Himanshu Pant, Mayank Sharma, Abhimanyu Dubey, Sumit Soman, Suraj Tripathi, Sai Guruju, Nihal Goalla
2021 arXiv   pre-print
We demonstrate the effectiveness of our formulation (the Low Complexity Neural Network - LCNN) across several deep learning algorithms, and a variety of large benchmark datasets.  ...  Modern neural network architectures for large-scale learning tasks have substantially higher model complexities, which makes understanding, visualizing and training these architectures difficult.  ...  We denote this learning rule as Low Complexity Neural Network (LCNN) rule, which adapts the model weights to minimize both empirical error on training data as well as the VC dimension of the classifier  ... 
arXiv:1707.09933v3 fatcat:7iw6yppcq5a27kyit3dzqr7t4u

Classifying muscle parameters with artificial neural networks and simulated lateral pinch data

Kalyn M. Kearney, Joel B. Harley, Jennifer A. Nichols, Katherine Saul
2021 PLoS ONE  
Both neural networks classified these groups from lateral pinch force alone.  ...  We aimed to leverage musculoskeletal models and artificial neural networks to classify one Hill-type muscle parameter (maximum isometric force) from easily measurable dynamometric data (simulated lateral  ...  We hypothesized that the LSTM model would classify maximum isometric force with greater accuracy than the feedforward model, but both models would decrease in accuracy as dataset complexity increased.  ... 
doi:10.1371/journal.pone.0255103 pmid:34473706 pmcid:PMC8412284 fatcat:w7qtdcgynzfv5ebgunc66arqze

Design of Near-Optimal Classifier Using Multi-Layer Perceptron Neural Networks for Intelligent Sensors

Nadir N. Charniya
2013 International Journal of Modeling and Optimization  
Index Terms-Classifier, neural networks, multi-layer percptron, intelligent sensors.  ...  This paper presents the methodology and challenges in the design of near-optimal MLP NN based classifier with maximize classification accuracy under the constraints of minimum network dimension for implementation  ...  Neural networks are intrinsically capable of recognizing a complex pattern [1] .  ... 
doi:10.7763/ijmo.2013.v3.234 fatcat:4isht45qwza6lhxlt5elvfrkcm

A Study on the Prediction of Program Complexity Section for Offloading Execution Decision

Jaehyun Kim, Yangsun Lee
2019 International Journal of Control and Automation  
In this paper, we predicted a program area complexity based on deep learning to solve this problem.  ...  The program complexity area prediction predicts the execution complexity of the program by learning the program complexity estimate and actual execution complexity analyzed by the static profiler.  ...  learned neural network model is False, with the actual answer being True Table I .  ... 
doi:10.33832/ijca.2019.12.8.10 fatcat:juw32vmvbfg2niwgb4wjvcfnky

Integration of Static and Dynamic Analysis for Malware Family Classification with Composite Neural Network [article]

Yao Saint Yen, Zhe Wei Chen, Ying Ren Guo, Meng Chang Chen
2019 arXiv   pre-print
In this paper, we combine static and dynamic analysis features with deep neural networks for Windows malware classification.  ...  Given these features, we conduct experiments with composite neural network, showing that the proposed approach performs best with an accuracy of 83.17% on a total of 80 malware families with 4519 malware  ...  [5] proposed a model that used machine learnings convolution neural network to classify images extracted from malware binaries. Kim et al.  ... 
arXiv:1912.11249v1 fatcat:sz5fndjgiffn3b5y2aiafjdcua

A Survey on Multistage lung cancer Detection and Classification

Jay Jawarkar, Nishit Solanki, Meet Vaishnav, Harsh Vichare, Sheshang Degadwala
2020 International Journal of Scientific Research in Computer Science Engineering and Information Technology  
In this re- search we compare different Machine learning (SVM, KNN, RF etc.) techniques with deep learning (CNN, CDNN) techniques using different parameters accuracy, precision and recall.  ...  Earlier, Lung cancer is the primary cause of cancer deaths worldwide among both men and women, with more than 1 million deaths annually.  ...  A deep neural network (DNN) is an artificial neural network (ANN) with multiple Layers between the input and output layers.  ... 
doi:10.32628/cseit20631110 fatcat:hdzjvb22yfe7liuzaa3dvbpuey

Neural Network-Based Voting System with High Capacity and Low Computation for Intrusion Detection in SIEM/IDS Systems

Nabil Moukafih, Ghizlane Orhanou, Said El Hajji
2020 Security and Communication Networks  
This paper presents a majority system based on reliability approach that combines simple feedforward neural networks, as weak learners, and produces high detection capability with low computation resources  ...  The experimental results show that the model is very suitable for modeling a classification model with high accuracy and that its performance is superior to that of complex resource-intensive deep learning  ...  As for our weak neural networks, since the models are trained in parallel, we will only consider the model with the most complex architecture, which is NN3.  ... 
doi:10.1155/2020/3512737 fatcat:gdeonhd3szdonkygs4elrdk62i

Performance and efficiency: recent advances in supervised learning

Sheng Ma, Chuanyi Ji
1999 Proceedings of the IEEE  
Efficiency deals with the complexity of a learning machine in both space and time.  ...  for combinations of weak classifiers, and expectation and maximization algorithms for training static and dynamic neural networks.  ...  Barron for pointing out the issue of the existence of weak classifiers, and for helpful discussions. They would also like to thank T. K. Ho, G. Kleinberg, G. Nagy, and G.  ... 
doi:10.1109/5.784228 fatcat:eb2avzs7gjgdvj5in75eqntwoq

Research of assembling optimized classification algorithm by neural network based on Ordinary Least Squares (OLS)

Xinzheng Xu, Shifei Ding, Weikuan Jia, Gang Ma, Fengxiang Jin
2011 Neural computing & applications (Print)  
While recognizing complex high-dimensional data by neural network, the design of network is a challenge. Besides, single network model can hardly get satisfying recognition accuracy.  ...  The convergence rate of the classifier algorithm is fast, but the recognition precision is relatively low.  ...  The procedure of assembling optimization algorithm When facing with the complex processing problem, neural network based on feature dimension reduction is used to design the sub-classifier, although the  ... 
doi:10.1007/s00521-011-0694-3 fatcat:yjoxx3g6a5a57mggsravwp6umq

Deep Learning for Modulation Recognition: a Survey with a Demonstration

Ruolin Zhou, Fugang Liu, Christopher W. Gravelle
2020 IEEE Access  
In addition, we also apply a DL algorithm, convolutional neural network (CNN), to demonstrate the feasibility of using CNN to recognize and classify the over-the-air wireless signals using Mathworks DL  ...  In this paper, we review a variety of deep learning algorithms and models for modulation recognition and classification of wireless communication signals.  ...  This discovery not only solves the computational complexity of the neural network, but illustrates the superiority of the deep neural network in learning.  ... 
doi:10.1109/access.2020.2986330 fatcat:ywiz6qsseja5lllkqam4pm4xt4

Using Multioutput Learning to Diagnose Plant Disease and Stress Severity

Gianni Fenu, Francesca Maridina Malloci, Atif Khan
2021 Complexity  
The proposed model consists of a multioutput system based on convolutional neural networks.  ...  The deep learning approach considers five pretrained CNN architectures, namely, VGG-16, VGG-19, ResNet50, InceptionV3, MobileNetV2, and EfficientNetB0, as feature extractors to classify three diseases  ...  Considering the very low class, EfficientNetB0 gets better classifications, while MobileNetV2 tends to classify it with the low class. is may be due to the fact that the symptoms at this level are mild  ... 
doi:10.1155/2021/6663442 fatcat:4obgov7dkbaypp3mut3nbdi3om

Bridge Crack Identification Based on Feature Fusion of Convolutional Neural Networks

Qiuyue WANG, Baolin LI, Xiucai NIE
2019 DEStech Transactions on Computer Science and Engineering  
based on feature fusion of convolutional neural networks.  ...  Aiming at the problem of low image quality of bridge cracks and poor identification of bridge cracks by single convolutional neural network method, this paper proposes a bridge crack identification algorithm  ...  Algorithms based on deep learning theory. In this paper, the algorithm based on deep learning theory is used to classify the features extracted by two convolutional neural networks.  ... 
doi:10.12783/dtcse/iccis2019/31993 fatcat:kjzhimsagnb7pb4kg7rxzkqb24

Radio Frequency Fingerprint identification Based on Deep Complex Residual Network

Shenhua Wang, Hongliang Jiang, Xiaofang Fang, Yulong Ying, Jingchao Li, Bin Zhang
2020 IEEE Access  
Compared with real-valued neural networks, complex neural networks are easier to optimize and generalize, and have better learning potential.  ...  In addition, this paper uses residual learning to solve the problem of difficult training of deep complex convolutional neural network models and a radio frequency fingerprint Identification method based  ... 
doi:10.1109/access.2020.3037206 fatcat:w6db6j47und23mvx3sfq3qzwyy

Convolutional Neural Networks In Convolution [article]

Xiaobo Huang
2018 arXiv   pre-print
In contrast, We propose a novel wider Convolutional Neural Networks (CNN) architecture, motivated by the Multi-column Deep Neural Networks and the Network In Network(NIN), aiming for higher accuracy without  ...  Currently, increasingly deeper neural networks have been applied to improve their accuracy.  ...  The variances among each classifier are key to low generalization error of the ensemble. A CNNIC network, in light of ensemble learning, is an ensemble of weight-sharing classical CNNs.  ... 
arXiv:1810.03946v1 fatcat:7wvazgfsdzcy7i5px75r22fse4

Underwater target recognition method based on convolution residual network

Yuechao Chen, Shuanping Du, HengHeng Quan, Bin Zhou, V. Goussev, J. Yin
2019 MATEC Web of Conferences  
The underwater target radiated noises usually have characteristics of low signal to noise ratio, complex signal components and so on.  ...  The final recognition accuracies of the three convolutional residual networks are all over 93% and higher than that of normal convolutional neural network with 5 layers.  ...  Compared with traditional machine learning methods, the number of hidden layers in deep learning model is greatly increased, which greatly improves the ability of complex computing.  ... 
doi:10.1051/matecconf/201928304011 fatcat:ducyjayguzdudpk3653axxndi4
« Previous Showing results 1 — 15 out of 189,978 results