Filters








925 Hits in 7.0 sec

Deep Graph Mapper: Seeing Graphs Through the Neural Lens

Cristian Bodnar, Cătălina Cangea, Pietro Liò
2021 Frontiers in Big Data  
We demonstrate the suitability of Mapper as a topological framework for graph pooling by proving that Mapper is a generalization of pooling methods based on soft cluster assignments.  ...  Additionally, we use our method to produce GNN-aided visualisations of attributed complex networks.  ...  We now turn our attention to the latter. 7.1 Visualisations in Supervised Learning The first application of DGM is in a supervised learning context, where FIGURE 3 .  ... 
doi:10.3389/fdata.2021.680535 fatcat:jaw43rljnzbpnbexflhipk7eiy

The State of the Art in Integrating Machine Learning into Visual Analytics

A. Endert, W. Ribarsky, C. Turkay, B.L. William Wong, I. Nabney, I. Díaz Blanco, F. Rossi
2017 Computer graphics forum (Print)  
Further, it presents opportunities and challenges to enhance the synergy between machine learning and visual analytics for impactful future research directions.  ...  Visual analytics systems combine machine learning or other analytic techniques with interactive data visualization to promote sensemaking and analytical reasoning.  ...  This specific type of user feedback in the form of labelling new examples is exactly the focus of the active learning framework [Set09] in machine learning.  ... 
doi:10.1111/cgf.13092 fatcat:twl3cmkb5re2pmihg6dquwe7by

A Bioconductor workflow for processing and analysing spatial proteomics data

Lisa M. Breckels, Claire M. Mulvey, Kathryn S. Lilley, Laurent Gatto
2016 F1000Research  
We then demonstrate the application and interpretation of statistical learning methods, including novelty detection using semi-supervised learning, classification, clustering and transfer learning and  ...  We describe the software infrastructure at hand, importing and processing data, quality control, sub-cellular marker definition, visualisation and interactive exploration.  ...  the Higher Education Funding Council for England and funding from the Science and Technology Facilities Council.  ... 
doi:10.12688/f1000research.10411.1 pmid:30079225 pmcid:PMC6053703 fatcat:lmf5e26cfza7plwtmoikwfnrfe

Representation Learning for Fine-Grained Change Detection

Niall O'Mahony, Sean Campbell, Lenka Krpalkova, Anderson Carvalho, Joseph Walsh, Daniel Riordan
2021 Sensors  
Our research focuses on methods of harnessing the latent metric space of representation learning techniques as an interim output for hybrid human-machine intelligence.  ...  This review focuses on the state-of-the-art methods, applications, and challenges of representation learning for fine-grained change detection.  ...  Acknowledgments: The authors wish to acknowledge the DJEI/DES/SFI/HEA Irish Centre for High-End Computing (ICHEC) for the provision of computational facilities and support.  ... 
doi:10.3390/s21134486 pmid:34209075 fatcat:2shbcyvutvfbhhqrsmjipjdrzi

A Bioconductor workflow for processing and analysing spatial proteomics data

Lisa M. Breckels, Claire M. Mulvey, Kathryn S. Lilley, Laurent Gatto
2018 F1000Research  
We then demonstrate the application and interpretation of statistical learning methods, including novelty detection using semi-supervised learning, classification, clustering and transfer learning and  ...  We describe the software infrastructure at hand, importing and processing data, quality control, sub-cellular marker definition, visualisation and interactive exploration.  ...  the Higher Education Funding Council for England and funding from the Science and Technology Facilities Council.  ... 
doi:10.12688/f1000research.10411.2 fatcat:7t5jc3frf5bkfcumxcnemhkg7y

Machine learning and applications in microbiology

Stephen J Goodswen, Joel L N Barratt, Paul J Kennedy, Alexa Kaufer, Larissa Calarco, John T Ellis
2021 FEMS Microbiology Reviews  
These key points are further reinforced with an evaluation of how machine learning has been applied so far in a broad scope of real-life microbiology examples.  ...  Applying machine learning to address biological problems is expected to grow at an unprecedented rate, yet it is perceived by the uninitiated as a mysterious and daunting entity entrusted to the domain  ...  A typical interactive cycle for training a supervised machine learning model. The diagram represents one cycle of training (i.e. create model, predict, test and generate model parameters).  ... 
doi:10.1093/femsre/fuab015 pmid:33724378 pmcid:PMC8498514 fatcat:v6sobinw45b3rdecprof4k62su

Modelling Peri-Perceptual Brain Processes in a Deep Learning Spiking Neural Network Architecture

Zohreh Gholami Doborjeh, Nikola Kasabov, Maryam Gholami Doborjeh, Alexander Sumich
2018 Scientific Reports  
Some software modules used for the exemplar implementation of the proposed models and for the experiments included in the paper can be found at: http://www.kedri.aut.ac.nz/neucube/.  ...  The authors are indebted to the reviewers for their useful comments and suggestions that we consider as significant contribution to the quality of this paper.  ...  Supervised Learning and Classification using a SNN Classifier.  ... 
doi:10.1038/s41598-018-27169-8 pmid:29892002 pmcid:PMC5995966 fatcat:lkq7js5sxbeo5iggbs2yuyfsw4

A Review of Feature Selection and Feature Extraction Methods Applied on Microarray Data

Zena M. Hira, Duncan F. Gillies
2015 Advances in Bioinformatics  
Their advantages and disadvantages are outlined in order to provide a clearer idea of when to use each one of them for saving computational time and resources.  ...  We present some of the most popular methods for selecting significant features and provide a comparison between them.  ...  Conflict of Interests The authors declare that there is no conflict of interests regarding the publication of this paper.  ... 
doi:10.1155/2015/198363 pmid:26170834 pmcid:PMC4480804 fatcat:mnlyfcwcarhqjix63e46x63nka

Towards the next generation of exergames: Flexible and personalised assessment-based identification of tennis swings [article]

Boris Bačić
2018 arXiv   pre-print
The presented solution is able to learn from a small dataset and capture two subjective swing-technique assessment criteria from a coach.  ...  Personalised and flexible assessment criteria required for players of diverse skill levels and various coaching scenarios were demonstrated by assigning different labelling criteria for identifying similar  ...  Ian Nabney and Dr. Christopher Bishop for sharing and updating their source code for Netlab and RBF for the past two decades.  ... 
arXiv:1804.06948v2 fatcat:7sd3lijxnzbetkb5gn4dkqcxsa

Evolving spatio-temporal data machines based on the NeuCube neuromorphic framework: Design methodology and selected applications

Nikola Kasabov, Nathan Matthew Scott, Enmei Tu, Stefan Marks, Neelava Sengupta, Elisa Capecci, Muhaini Othman, Maryam Gholami Doborjeh, Norhanifah Murli, Reggio Hartono, Josafath Israel Espinosa-Ramos, Lei Zhou (+8 others)
2016 Neural Networks  
and functionality, can be visualised and interpreted for new knowledge discovery and for a better understanding of the data and the processes that generated it. eSTDM can be used for early event prediction  ...  A framework for building eSTDM called NeuCube along with a design methodology for building eSTDM using it is presented.  ...  Related papers, data, and software systems can be found at http:// www.kedri.aut.ac.nz and http://ncs.ethz/projects/ evospike/, where a NeuCube simulator can be downloaded free for use in research and  ... 
doi:10.1016/j.neunet.2015.09.011 pmid:26576468 fatcat:hytvg4eekjfazd4244z3o6cmdu

Untangling urban data signatures: unsupervised machine learning methods for the detection of urban archetypes at the pedestrian scale [article]

Gareth D. Simons
2022 arXiv   pre-print
The methods are applied to a dataset for Greater London consisting of network centralities, land-use accessibilities, mixed-use measures, and density measures.  ...  Data science and machine learning (ML) methods provide an opportunity to explore such forms of complex datasets by applying unsupervised ML methods to reduce the dimensionality of the data while recovering  ...  A knee-jerk reaction may be to reject machine learning out-of-hand for its links to mathematics and statistics more generally; however, on closer scrutiny, the synthesis of spatially precise urban morphological  ... 
arXiv:2106.15363v3 fatcat:ww637kegb5ekvhmpndsu2jkyqe

A Survey of Link Mining and Anomalies Detection

Zakea Idris Ali
2016 International Journal of Data Mining & Knowledge Management Process  
Web mining is the extraction of interesting and potentially useful patterns and implicit information from activity related to the World Wide Web whereas link mining, focuses on discovering explicit links  ...  These tools involve mathematical algorithms, machine-learning methods and statistical models, and applications such as banking, insurance and medicine; while text mining has been applied to semi-structured  ...  Clustering is often called an unsupervised learning task, as no class values indicate an a priori grouping of the data instances, as in the case for supervised learning.  ... 
doi:10.5121/ijdkp.2016.6201 fatcat:iwfrrosfe5b5lfj27vdt6nz6uu

Bridging Information Visualization with Machine Learning (Dagstuhl Seminar 15101)

Daniel A. Keim, Tamara Munzner, Fabrice Rossi, Michael Verleysen, Marc Herbstritt
2015 Dagstuhl Reports  
This seminar is a successor to Dagstuhl seminar 12081 "Information Visualization, Visual Data Mining and Machine Learning" held in 2012.  ...  This report documents the program and the outcomes of Dagstuhl Seminar 15101 "Bridging Information Visualization with Machine Learning".  ...  This calls for a combination of the two fields, such that it becomes possible to address these challenged with integrated methods which can automate inference wherever possible, but which can use interactive  ... 
doi:10.4230/dagrep.5.3.1 dblp:journals/dagstuhl-reports/KeimMRV15 fatcat:tkowwfgn5baonczdk24lus5sea

Developments in data science solutions for carnivore tooth pit classification

Lloyd A. Courtenay, Darío Herranz-Rodrigo, Diego González-Aguilera, José Yravedra
2021 Scientific Reports  
While numerous techniques already exist for the detection of carnivore activity in archaeological and palaeontological sites, many of these techniques present important limitations.  ...  For the purpose of this study, a large sample of 620 carnivore tooth pits is presented, including samples from bears, hyenas, jaguars, leopards, lions, wolves, foxes and African wild dogs.  ...  Among the researchers of TIDOP, we are particularly grateful for the useful comments and suggestions made by Roberto García, Susana del Pozo, and  ... 
doi:10.1038/s41598-021-89518-4 pmid:33986378 pmcid:PMC8119709 fatcat:n7vqzllh6ra2rgnttgvqfafbqq

Using EEG Data and NeuCube for the Study of Transfer of Learning

Mojgan Hafezi Fard, Krassie Petrova, Maryam Doborjeh, Nikola Kasabov
2020 2020 International Conference on Computational Science and Computational Intelligence (CSCI)  
Deeper and long-lasting learning occurs through a critical review of prior knowledge in the light of the new context, and a transfer of the acquired knowledge to new settings.  ...  The outcomes of this study are used to inform the design of a follow-up study where SNN models will be built from STBD gathered from participants engaged in learning and in TL.  ...  For a comparison analysis, we used the same dataset and ran the classification experiment with several conventional ML methods, namely Support Vector Machine (SVM), Multilayer Perceptron (MLP) and Multivariable  ... 
doi:10.1109/csci51800.2020.00082 fatcat:77d4gbog4jfgzjyulcf6k7lov4
« Previous Showing results 1 — 15 out of 925 results