Filters








286,791 Hits in 3.8 sec

Predicting Neural Network Accuracy from Weights [article]

Thomas Unterthiner, Daniel Keysers, Sylvain Gelly, Olivier Bousquet, Ilya Tolstikhin
2021 arXiv   pre-print
We show experimentally that the accuracy of a trained neural network can be predicted surprisingly well by looking only at its weights, without evaluating it on input data.  ...  Even when using simple statistics of the weights, the predictors are able to rank neural networks by their performance with very high accuracy (R2 score more than 0.98).  ...  Neural Network Accuracy from Weights C.  ... 
arXiv:2002.11448v4 fatcat:y4kcnejpefc6xcbznbl3o55iam

Combining neural network predictions for medical diagnosis

Yoichi Hayashi, Rudy Setiono
2002 Computers in Biology and Medicine  
We present our results from combining the predictions of an ensemble of neural networks for the diagnosis of hepatobiliary disorders.  ...  We discuss how the overall predictive accuracy can be improved by introducing bias during the training of the level one networks. ?  ...  , AveBNN is the best accuracy from averaging biased NN predictions, 2LNN is the best accuracy from the two-level neural network method.  ... 
doi:10.1016/s0010-4825(02)00006-9 pmid:11931862 fatcat:mru5s4nrdbhmdg6go26z22rwte

Prediction of Seismic zone in India using Neural Network Algorithms

2019 VOLUME-8 ISSUE-10, AUGUST 2019, REGULAR ISSUE  
The prediction of an earthquake is an important task in seismology. Neural network performs a key task in the prediction of earthquake.  ...  The developed network model was trained with set of data items using neural network algorithms such as Backpropagation and sequential learning.  ...  The foremost intention of this work is to evaluate the accuracy of the neural network prediction algorithms using the software tool.  ... 
doi:10.35940/ijitee.l2798.1081219 fatcat:ibl74ptywjeh3nb55eln45z4qy

Neural Networks Assist Crowd Predictions in Discerning the Veracity of Emotional Expressions [article]

Zhenyue Qin and Tom Gedeon and Sabrina Caldwell
2018 arXiv   pre-print
Neural networks can achieve an accuracy to 99.69% by aggregating participants' answers. That is, assigning positive and negative weights to high and low human predictors, respectively.  ...  We find that our neural networks do not require a large number of participants, particularly, 30 randomly selected, to achieve high accuracy predictions, better than any individual participant.  ...  Neural Networks A simple feedforward neural network [16] is utilized to give participants different weights in order to value high/low-quality responses differently.  ... 
arXiv:1808.05359v1 fatcat:x7ghgqr4fffazce2bpbb3gc47e

Protein Secondary Structure Prediction using Bayesian Inference method on Decision fusion algorithms

Somasheker Akkaladevi, Ajay K Katangur
2007 2007 IEEE International Parallel and Distributed Processing Symposium  
Decision fusion methods such as the Committee method and Correlation methods were also used in combination with the profile-based neural networks and AI algorithms for achieving better prediction accuracy  ...  Previously research was performed in this field using several techniques such as neural networks, Simulated annealing (SA) and Genetic algorithms (GA) for improving the protein secondary structure prediction  ...  neural network for weight adjustments.  ... 
doi:10.1109/ipdps.2007.370430 dblp:conf/ipps/AkkaladeviK07 fatcat:hugcawgrizfqbf5dhq6htiodae

Accuracy Enhancement of Artificial Neural Network using Genetic Algorithm

Preeti Gupta, Bikrampal Kaur
2014 International Journal of Computer Applications  
feed forward neural network and fitting neural network respectively for the accuracy enhancement percentage.  ...  This research paper proposes the enhancement of the accuracy of the results by using Artificial Neural Network optimized with Genetic Algorithm in prediction of heart disease diagnosis with UCI dataset  ...  It shows the accuracy enhancement from normal neural network to optimized neural network.  ... 
doi:10.5120/18133-9258 fatcat:nbllfvcqwzdwvch5p7rzicbtem

An Inter-Layer Weight Prediction and Quantization for Deep Neural Networks based on a Smoothly Varying Weight Hypothesis [article]

Kang-Ho Lee, JoonHyun Jeong, Sung-Ho Bae
2020 arXiv   pre-print
deep neural networks.  ...  Due to a resource-constrained environment, network compression has become an important part of deep neural networks research.  ...  affect the accuracy of neural networks.  ... 
arXiv:1907.06835v2 fatcat:ezwqjdkntzb3fjdufkmffmrroi

Comparison of Predictive Models for the Early Diagnosis of Diabetes

Meysam Jahani, Mahdi Mahdavi
2016 Healthcare Informatics Research  
In this study memetic algorithms were applied to update weights and improve the prediction accuracy of neural network models for diabetes prediction.  ...  Having improved the weight of neural network models, we obtained a memetic algorithm model that achieved 93% prediction accuracy.  ... 
doi:10.4258/hir.2016.22.2.95 pmid:27200219 pmcid:PMC4871851 fatcat:s4cj7adksvdorekq7hjvnxxq5a

Neural Network on Mortality Prediction for the Patient Admitted with ADHF (Acute Decompensated Heart Failure)

M. Haider Abu Yazid, Shukor Talib, Muhammad Haikal Satria, Azmee Abd Ghazi
2017 Proceeding of the Electrical Engineering Computer Science and Informatics  
Results show that artificial neural network can predict mortality for ADHF patient with good prediction accuracy of 94.73% accuracy for training dataset and 91.65% for test dataset.  ...  Keywords-mortality prediction, artificial neural network,acute decompensated heart failure I.  ...  ACKNOWLEDGMENT This research was a collaborative effort between University Technology of Malaysia (UTM) and National Heart Institute (IJN) Malaysia with approval from IJN Ethic Committee (Project Registration  ... 
doi:10.11591/eecsi.v4.1017 fatcat:ydbemuy2ufhrdj6ogfhfeawaxi

Artificial Neural Network Analysis of the Impact of Sample Output Accuracy

Yu Zhong Zhang, Shao Yun Song, R.K. Agarwal, H. Abd. Rahman
2016 MATEC Web of Conferences  
of artificial neural network output for the neural network, to improve the output of neural network accuracy is important.  ...  Quality sample study of neural network output accuracy is not much affected, most of the research is the structure (number of layers and the number of nodes), the impact of this paper to analyze samples  ...  It shows the effect on the accuracy of the neural network output removed after the i-th data point, From the accuracy portrayed the importance of the i-th data point.  ... 
doi:10.1051/matecconf/20166501011 fatcat:rhuxawyl7bcj7p5pobrxgw6qvu

Predicting protein secondary structure by cascade-correlation neural networks

M. J. Wood, J. D. Hirst
2004 Bioinformatics  
The back-propagation neural network algorithm is a commonly used method for predicting the secondary structure of proteins.  ...  MEDLINE Abstract Vivarelli,F. et al. (1997) The prediction of protein secondary structure with a cascade-correlation learning architecture of neural networks. Neural Comput. Appl., 6, 57-62.  ...  ., 1997) to achieve an average predictive accuracy of 76.5%. These neural network methods are based on the popular back-propagation algorithm.  ... 
doi:10.1093/bioinformatics/btg423 pmid:14960469 fatcat:jkvimh23t5g4xijyfhm7pperkm

Numerical Simulation of an InP Photonic Integrated Cross-Connect for Deep Neural Networks on Chip

Bin Shi, Nicola Calabretta, Ripalta Stabile
2020 Applied Sciences  
The iris flower classification problem is solved by implementing the weight matrix of a trained three-layer deep neural network.  ...  We propose a novel photonic accelerator architecture based on a broadcast-and-weight approach for a deep neural network through a photonic integrated cross-connect.  ...  Acknowledgments: The authors thank the technical support from VPIphotonics. Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.3390/app10020474 fatcat:uhjbuo3i3rg3zc33nsejw64hbe

Protein Secondary Structure Prediction using an Optimised Bayesian Classification Neural Network
english

Son T. Nguyen, Colin G. Johnson
2013 Proceedings of the 5th International Joint Conference on Computational Intelligence  
This paper describes the use of optimised classification Bayesian neural networks for the prediction of protein secondary structure.  ...  The well-known RS126 dataset was used for network training and testing. The experimental results show that the optimised classification Bayesian neural network can reach an accuracy greater than 75%.  ...  Table 2 shows the prediction accuracy and the Matthew's correlation coefficients on three states from the classification Bayesian neural network. We can see that the accuracy is 75.77%.  ... 
doi:10.5220/0004538604510457 dblp:conf/ijcci/NguyenJ13 fatcat:wpmycvg7tnex7llaiyibjzm3lm

Protein secondary structure prediction with a neural network

L. H. Holley, M. Karplus
1989 Proceedings of the National Academy of Sciences of the United States of America  
A method is presented for protein secondary structure prediction based on a neural network.  ...  In this paper* we describe a secondary structure prediction method that makes use of neural networks.  ...  In our case, however, a neural network without hidden units is able to achieve a predictive accuracy that is close to optimal.  ... 
doi:10.1073/pnas.86.1.152 pmid:2911565 pmcid:PMC286422 fatcat:c4dlphxxojdojdorfcx6uv6wr4

Predicting genotypic values associated with gene interactions using neural networks: A simulation study for investigating factors affecting prediction accuracy [article]

Akio Onogi
2019 bioRxiv   pre-print
Neural networks including deep neural networks are attractive candidates to predict phenotypic values.  ...  However, the properties of neural networks in predicting non-additive effects have not been clarified.  ...  ., a subset of networks that can achieve equivalent accuracy as the original model after training in isolation) from randomly initialized weights [38] .  ... 
doi:10.1101/2019.12.18.881912 fatcat:ctnxnjzysjgspcxny5jl7znrgu
« Previous Showing results 1 — 15 out of 286,791 results