A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Filters
Structured Differential Learning for Automatic Threshold Setting
[article]
2018
arXiv
pre-print
Preserved Fulltext
We introduce a technique that can automatically tune the parameters of a rule-based computer vision system comprised of thresholds, combinational logic, and time constants. ...
We describe the components of the system and the associated supervised learning mechanism. ...
Structured Differential Learning for Automatic Threshold Setting Jonathan H. Connell, Benjamin W. Herta IBM T.J. ...
arXiv:1808.00361v1
fatcat:bclkdigtxfh2tbzis3ey5kzcxm
How to do Physics-based Learning
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
Specifically, we advocate exploiting the auto-differentiation functionality twice, once to build a physics-based network and again to perform physics-based learning. ...
The goal of this tutorial is to explain step-by-step how to implement physics-based learning for the rapid prototyping of a computational imaging system. ...
Soft thresholding is used as the proximal operator. the create graph flag of the automatic differentiator to True. ...
arXiv:2005.13531v2
fatcat:3xrzhgu42fel3dqdpg2ilnmvmq
Embedding Differentiable Sparsity into Deep Neural Network
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Thus, it can learn the sparsified structure and the weights of networks simultaneously. The proposed approach can learn structured as well as unstructured sparsity. ...
In this paper, we propose embedding sparsity into the structure of deep neural networks, where model parameters can be exactly zero during training with the stochastic gradient descent. ...
Coarse Gradient for Threshold Operation If the magnitude of a parameter or a group is less than a threshold, it is zeroed-out by relu and it does not receive a learning signal since the gradient of relu ...
arXiv:2006.13716v1
fatcat:xu64fnwz2ndktdhkge2rssquxq
Automatic Clustering Using FSDE-Forced Strategy Differential Evolution
2018
Journal of Physics, Conference Series
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2018; you can also visit the original URL.
The file type is application/pdf.
This study intends on acquiring cluster number automatically utilizing forced strategy differential evolution (AC-FSDE). ...
Clustering analysis is important in datamining for unsupervised data, cause no adequate prior knowledge. ...
The result shows that automatic clustering using forced strategy of differential evolution (AC-FSDE) more competitive than automatic clustering algorithm based differential evolution (ACDE). ...
doi:10.1088/1742-6596/953/1/012127
fatcat:mxcum7io4fevfjjgeu6on6l4cq
Deep Learning Classification for Diabetic Foot Thermograms
2020
Sensors
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
This paper compares machine learning-based techniques with Deep Learning (DL) structures. We tested common structures in the mode of transfer learning, including AlexNet and GoogleNet. ...
The main goal of this work is to analyze the use of AI and DL for the classification of diabetic foot thermograms, highlighting their advantages and limitations. ...
a) RGB image b) Grayscale c) 1 Threshold d) 2 Thresholds e) 3 Thresholds f) 4 Thresholds This automatic segmentation based on DE defines the thresholds of fuzzy sets. ...
doi:10.3390/s20061762
pmid:32235780
fatcat:54mue3jv6vdbtar6t5clipym7m
Automatic Interferogram Selection for SBAS-InSAR Based on Deep Convolutional Neural Networks
2021
Remote Sensing
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Especially in the era of big data, the demand for an automatic and effective selection method of high-quality interferograms in SBAS-InSAR technology is growing. ...
It is concluded that DCNN algorithms can automatically select high quality interferogram for the SBAS-InSAR method and thus have a significant impact on the precision of surface deformation monitoring. ...
Acknowledgments: The authors like to thank the anonymous reviewers for their efforts and constructive comments to improve the quality of this paper. ...
doi:10.3390/rs13214468
fatcat:ndto6cjnmjga3lblcqogqkkstu
Automated segmentation technique with self-driven post-processing for histopathological breast cancer images
2020
CAAI Transactions on Intelligence Technology
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
area opening, fill holes and selects most appropriate enhanced image required for further analysis. ...
The post-processing method itself determines the value of different parameters for different operations based on segmented results obtained. ...
Automated threshold selection reduces the need for initial level set, time step, weighted area coefficient parameters setting. ...
doi:10.1049/trit.2019.0077
fatcat:yafdhjlaorgyfccfjspqsjcroi
Neuron segmentation in electron microscopy images using partial differential equations
2013
2013 IEEE 10th International Symposium on Biomedical Imaging
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is application/pdf.
We also introduce a new method for representing the resulting image that allows for a more dynamic thresholding to further improve the result. ...
Here we present a partial differential equation with a novel growth term to improve the results of a supervised learning algorithm. ...
Figure 2 (c) shows that narrow dark structures will have a larger positive value for λ 1 that when subtracted will sharpen membrane structures. ...
doi:10.1109/isbi.2013.6556809
pmid:25143802
pmcid:PMC4136503
dblp:conf/isbi/JonesSET13
fatcat:ybvvovdlgzbfrm7aqartkvebwe
Scalable learning of interpretable rules for the dynamic microbiome domain
[article]
2020
biorxiv/medrxiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
We present a new fully-differentiable model that also learns human-interpretable rules for the same classification task, but in an end-to-end gradient-descent based framework. ...
and moreover learning a larger set of rules, thus providing additional biological insight into the effects of diet and environment on the microbiome. ...
Differentiable rule learning. ...
doi:10.1101/2020.06.25.172270
fatcat:5oxpacwayzhbzlceoc2zwnv3ta
Machine Learning Versus Human-Developed Algorithms in Image Analysis of Microstructures
2019
Quality Production Improvement - QPI
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Automatically prepared solutions, based on machine learning, constitute an effective and sufficiently precise tool for classification. ...
Automatic image analysis is nowadays a standard method in quality control of metallic materials, especially in grain size, graphite shape and non-metallic content evaluation. ...
This is due to the necessity of collecting large data sets for training purposes. The images should be of good quality and represent representative differentiation of microstructures. ...
doi:10.2478/cqpi-2019-0056
fatcat:mivgmwsxxrerzowwe2ulxjsbsy
Parameter learning with truncated message-passing
2011
CVPR 2011
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2013; you can also visit the original URL.
The file type is application/pdf.
However, truncated fitting is much faster for learning.
Table 1. A summary of the experimental setting. ...
Namely, one need not store all intermediate values, as in standard automatic differentiation. ...
doi:10.1109/cvpr.2011.5995320
dblp:conf/cvpr/Domke11
fatcat:6oky7bc67reijfmqbs4mrtjsza
Latent Patient Network Learning for Automatic Diagnosis
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
To this end, we propose a novel, end-to-end trainable graph learning architecture for dynamic and localized graph pruning. ...
Recently, Graph Convolutional Networks (GCNs) has proven to be a powerful machine learning tool for Computer Aided Diagnosis (CADx) and disease prediction. ...
Predicting a discrete (e.g. binary) graph structure is a non-differentiable problem. ...
arXiv:2003.13620v1
fatcat:cdfxbi5sezaobil4xuc4xrnqum
Differentiable Signal Processing With Black-Box Audio Effects
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
commercial solution for music mastering. ...
To train our network with non-differentiable black-box effects layers, we use a fast, parallel stochastic gradient approximation scheme within a standard auto differentiation graph, yielding efficient ...
) [11, 12] , where signal processing structures are implemented within a deep learning auto-differentiation framework and trained via backpropagation. ...
arXiv:2105.04752v1
fatcat:j3n5i7q22ndobgpzedaybkt5qa
Focal edge association to glaucoma diagnosis
2011
2011 Annual International Conference of the IEEE Engineering in Medicine and Biology Society
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
The association between focal edges and angle grades is built through machine learning. A modified grading system with three grades is adopted. ...
Moreover, it can correctly classify 75.0% grade 1 and 77.4% grade 0 for angle closure cases. ...
For the threshold approach, we can introduce another threshold T 2 to differentiate grade 1 from grade 0. We compute the mean width w as in [4] . ...
doi:10.1109/iembs.2011.6091111
pmid:22255334
dblp:conf/embc/ChengLWTLCBWA11
fatcat:pzj7wtiylnbercvg73gnj5tu4m
Abstracts of Current Computer Literature
1968
IEEE transactions on computers
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2015; you can also visit the original URL.
The file type is application/pdf.
In this manner the automaton is said to possess a variable structure and the ability to learn. ...
The equivalence is established through a set of defining equations similar to that of a single-threshold threshold element. ...
doi:10.1109/tc.1968.227415
fatcat:gww3av6fqncynbg6czmzjuomxi
« Previous
Showing results 1 — 15 out of 118,357 results