On the Correlation between Reservoir Metrics and Performance for Time Series Classification under the Influence of Synaptic Plasticity
Events
Loading … Spinner

Mendeley | Further Information

{"title"=>"On the correlation between reservoir metrics and performance for time series classification under the influence of synaptic plasticity", "type"=>"journal", "authors"=>[{"first_name"=>"Joseph", "last_name"=>"Chrol-Cannon", "scopus_author_id"=>"55337989400"}, {"first_name"=>"Yaochu", "last_name"=>"Jin", "scopus_author_id"=>"8938826600"}], "year"=>2014, "source"=>"PLoS ONE", "identifiers"=>{"pui"=>"373524466", "sgr"=>"84904244223", "issn"=>"19326203", "pmid"=>"25010415", "scopus"=>"2-s2.0-84904244223", "doi"=>"10.1371/journal.pone.0101792"}, "id"=>"a0c40101-3505-3c59-a54f-24527f982e26", "abstract"=>"Reservoir computing provides a simpler paradigm of training recurrent networks by initialising and adapting the recurrent connections separately to a supervised linear readout. This creates a problem, though. As the recurrent weights and topology are now separated from adapting to the task, there is a burden on the reservoir designer to construct an effective network that happens to produce state vectors that can be mapped linearly into the desired outputs. Guidance in forming a reservoir can be through the use of some established metrics which link a number of theoretical properties of the reservoir computing paradigm to quantitative measures that can be used to evaluate the effectiveness of a given design. We provide a comprehensive empirical study of four metrics; class separation, kernel quality, Lyapunov’s exponent and spectral radius. These metrics are each compared over a number of repeated runs, for different reservoir computing set-ups that include three types of network topology and three mechanisms of weight adaptation through synaptic plasticity. Each combination of these methods is tested on two time-series classification problems. We find that the two metrics that correlate most strongly with the classification performance are Lyapunov’s exponent and kernel quality. It is also evident in the comparisons that these two metrics both measure a similar property of the reservoir dynamics. We also find that class separation and spectral radius are both less reliable and less effective in predicting performance.", "link"=>"http://www.mendeley.com/research/correlation-between-reservoir-metrics-performance-time-series-classification-under-influence-synapti", "reader_count"=>30, "reader_count_by_academic_status"=>{"Professor > Associate Professor"=>1, "Researcher"=>6, "Student > Ph. D. Student"=>6, "Student > Postgraduate"=>4, "Student > Master"=>11, "Professor"=>2}, "reader_count_by_user_role"=>{"Professor > Associate Professor"=>1, "Researcher"=>6, "Student > Ph. D. Student"=>6, "Student > Postgraduate"=>4, "Student > Master"=>11, "Professor"=>2}, "reader_count_by_subject_area"=>{"Engineering"=>9, "Unspecified"=>1, "Environmental Science"=>1, "Materials Science"=>1, "Agricultural and Biological Sciences"=>1, "Neuroscience"=>2, "Physics and Astronomy"=>4, "Computer Science"=>10, "Economics, Econometrics and Finance"=>1}, "reader_count_by_subdiscipline"=>{"Engineering"=>{"Engineering"=>9}, "Materials Science"=>{"Materials Science"=>1}, "Neuroscience"=>{"Neuroscience"=>2}, "Physics and Astronomy"=>{"Physics and Astronomy"=>4}, "Economics, Econometrics and Finance"=>{"Economics, Econometrics and Finance"=>1}, "Agricultural and Biological Sciences"=>{"Agricultural and Biological Sciences"=>1}, "Computer Science"=>{"Computer Science"=>10}, "Unspecified"=>{"Unspecified"=>1}, "Environmental Science"=>{"Environmental Science"=>1}}, "reader_count_by_country"=>{"Belgium"=>1, "United States"=>1, "Slovakia"=>1, "Germany"=>1}, "group_count"=>2}

Scopus | Further Information

{"@_fa"=>"true", "link"=>[{"@_fa"=>"true", "@ref"=>"self", "@href"=>"https://api.elsevier.com/content/abstract/scopus_id/84904244223"}, {"@_fa"=>"true", "@ref"=>"author-affiliation", "@href"=>"https://api.elsevier.com/content/abstract/scopus_id/84904244223?field=author,affiliation"}, {"@_fa"=>"true", "@ref"=>"scopus", "@href"=>"https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=84904244223&origin=inward"}, {"@_fa"=>"true", "@ref"=>"scopus-citedby", "@href"=>"https://www.scopus.com/inward/citedby.uri?partnerID=HzOxMe3b&scp=84904244223&origin=inward"}], "prism:url"=>"https://api.elsevier.com/content/abstract/scopus_id/84904244223", "dc:identifier"=>"SCOPUS_ID:84904244223", "eid"=>"2-s2.0-84904244223", "dc:title"=>"On the correlation between reservoir metrics and performance for time series classification under the influence of synaptic plasticity", "dc:creator"=>"Chrol-Cannon J.", "prism:publicationName"=>"PLoS ONE", "prism:eIssn"=>"19326203", "prism:volume"=>"9", "prism:issueIdentifier"=>"7", "prism:pageRange"=>nil, "prism:coverDate"=>"2014-07-10", "prism:coverDisplayDate"=>"10 July 2014", "prism:doi"=>"10.1371/journal.pone.0101792", "citedby-count"=>"5", "affiliation"=>[{"@_fa"=>"true", "affilname"=>"University of Surrey", "affiliation-city"=>"Guildford", "affiliation-country"=>"United Kingdom"}], "pubmed-id"=>"25010415", "prism:aggregationType"=>"Journal", "subtype"=>"ar", "subtypeDescription"=>"Article", "article-number"=>"e101792", "source-id"=>"10600153309", "openaccess"=>"1", "openaccessFlag"=>true}

Facebook

  • {"url"=>"http%3A%2F%2Fjournals.plos.org%2Fplosone%2Farticle%3Fid%3D10.1371%252Fjournal.pone.0101792", "share_count"=>0, "like_count"=>0, "comment_count"=>0, "click_count"=>0, "total_count"=>0}

Counter

  • {"month"=>"7", "year"=>"2014", "pdf_views"=>"25", "xml_views"=>"9", "html_views"=>"128"}
  • {"month"=>"8", "year"=>"2014", "pdf_views"=>"5", "xml_views"=>"2", "html_views"=>"30"}
  • {"month"=>"9", "year"=>"2014", "pdf_views"=>"3", "xml_views"=>"1", "html_views"=>"39"}
  • {"month"=>"10", "year"=>"2014", "pdf_views"=>"5", "xml_views"=>"3", "html_views"=>"33"}
  • {"month"=>"11", "year"=>"2014", "pdf_views"=>"11", "xml_views"=>"2", "html_views"=>"48"}
  • {"month"=>"12", "year"=>"2014", "pdf_views"=>"2", "xml_views"=>"2", "html_views"=>"26"}
  • {"month"=>"1", "year"=>"2015", "pdf_views"=>"6", "xml_views"=>"0", "html_views"=>"30"}
  • {"month"=>"2", "year"=>"2015", "pdf_views"=>"3", "xml_views"=>"0", "html_views"=>"17"}
  • {"month"=>"3", "year"=>"2015", "pdf_views"=>"6", "xml_views"=>"0", "html_views"=>"17"}
  • {"month"=>"4", "year"=>"2015", "pdf_views"=>"5", "xml_views"=>"0", "html_views"=>"21"}
  • {"month"=>"5", "year"=>"2015", "pdf_views"=>"6", "xml_views"=>"1", "html_views"=>"19"}
  • {"month"=>"6", "year"=>"2015", "pdf_views"=>"14", "xml_views"=>"0", "html_views"=>"39"}
  • {"month"=>"7", "year"=>"2015", "pdf_views"=>"1", "xml_views"=>"0", "html_views"=>"10"}
  • {"month"=>"8", "year"=>"2015", "pdf_views"=>"2", "xml_views"=>"0", "html_views"=>"11"}
  • {"month"=>"9", "year"=>"2015", "pdf_views"=>"2", "xml_views"=>"1", "html_views"=>"8"}
  • {"month"=>"10", "year"=>"2015", "pdf_views"=>"3", "xml_views"=>"0", "html_views"=>"15"}
  • {"month"=>"11", "year"=>"2015", "pdf_views"=>"8", "xml_views"=>"0", "html_views"=>"19"}
  • {"month"=>"12", "year"=>"2015", "pdf_views"=>"2", "xml_views"=>"0", "html_views"=>"16"}
  • {"month"=>"1", "year"=>"2016", "pdf_views"=>"7", "xml_views"=>"0", "html_views"=>"23"}
  • {"month"=>"2", "year"=>"2016", "pdf_views"=>"3", "xml_views"=>"0", "html_views"=>"16"}
  • {"month"=>"3", "year"=>"2016", "pdf_views"=>"2", "xml_views"=>"0", "html_views"=>"30"}
  • {"month"=>"4", "year"=>"2016", "pdf_views"=>"5", "xml_views"=>"0", "html_views"=>"9"}
  • {"month"=>"5", "year"=>"2016", "pdf_views"=>"6", "xml_views"=>"0", "html_views"=>"15"}
  • {"month"=>"6", "year"=>"2016", "pdf_views"=>"4", "xml_views"=>"0", "html_views"=>"17"}
  • {"month"=>"7", "year"=>"2016", "pdf_views"=>"5", "xml_views"=>"0", "html_views"=>"14"}
  • {"month"=>"8", "year"=>"2016", "pdf_views"=>"4", "xml_views"=>"0", "html_views"=>"14"}
  • {"month"=>"9", "year"=>"2016", "pdf_views"=>"13", "xml_views"=>"0", "html_views"=>"28"}
  • {"month"=>"10", "year"=>"2016", "pdf_views"=>"7", "xml_views"=>"0", "html_views"=>"22"}
  • {"month"=>"11", "year"=>"2016", "pdf_views"=>"1", "xml_views"=>"0", "html_views"=>"16"}
  • {"month"=>"12", "year"=>"2016", "pdf_views"=>"2", "xml_views"=>"0", "html_views"=>"14"}
  • {"month"=>"1", "year"=>"2017", "pdf_views"=>"0", "xml_views"=>"0", "html_views"=>"25"}
  • {"month"=>"2", "year"=>"2017", "pdf_views"=>"9", "xml_views"=>"0", "html_views"=>"37"}
  • {"month"=>"3", "year"=>"2017", "pdf_views"=>"7", "xml_views"=>"0", "html_views"=>"31"}
  • {"month"=>"4", "year"=>"2017", "pdf_views"=>"7", "xml_views"=>"0", "html_views"=>"24"}
  • {"month"=>"5", "year"=>"2017", "pdf_views"=>"2", "xml_views"=>"0", "html_views"=>"34"}
  • {"month"=>"6", "year"=>"2017", "pdf_views"=>"1", "xml_views"=>"0", "html_views"=>"19"}
  • {"month"=>"7", "year"=>"2017", "pdf_views"=>"7", "xml_views"=>"2", "html_views"=>"18"}
  • {"month"=>"8", "year"=>"2017", "pdf_views"=>"3", "xml_views"=>"3", "html_views"=>"18"}
  • {"month"=>"9", "year"=>"2017", "pdf_views"=>"5", "xml_views"=>"0", "html_views"=>"16"}
  • {"month"=>"10", "year"=>"2017", "pdf_views"=>"4", "xml_views"=>"2", "html_views"=>"31"}
  • {"month"=>"11", "year"=>"2017", "pdf_views"=>"5", "xml_views"=>"1", "html_views"=>"30"}
  • {"month"=>"12", "year"=>"2017", "pdf_views"=>"1", "xml_views"=>"2", "html_views"=>"12"}
  • {"month"=>"1", "year"=>"2018", "pdf_views"=>"3", "xml_views"=>"2", "html_views"=>"7"}
  • {"month"=>"2", "year"=>"2018", "pdf_views"=>"1", "xml_views"=>"0", "html_views"=>"4"}
  • {"month"=>"3", "year"=>"2018", "pdf_views"=>"6", "xml_views"=>"0", "html_views"=>"10"}
  • {"month"=>"4", "year"=>"2018", "pdf_views"=>"13", "xml_views"=>"0", "html_views"=>"6"}
  • {"month"=>"5", "year"=>"2018", "pdf_views"=>"3", "xml_views"=>"0", "html_views"=>"6"}
  • {"month"=>"6", "year"=>"2018", "pdf_views"=>"2", "xml_views"=>"1", "html_views"=>"2"}
  • {"month"=>"7", "year"=>"2018", "pdf_views"=>"3", "xml_views"=>"3", "html_views"=>"4"}
  • {"month"=>"8", "year"=>"2018", "pdf_views"=>"2", "xml_views"=>"1", "html_views"=>"4"}
  • {"month"=>"9", "year"=>"2018", "pdf_views"=>"3", "xml_views"=>"0", "html_views"=>"5"}
  • {"month"=>"10", "year"=>"2018", "pdf_views"=>"3", "xml_views"=>"1", "html_views"=>"5"}
  • {"month"=>"11", "year"=>"2018", "pdf_views"=>"1", "xml_views"=>"0", "html_views"=>"2"}
  • {"month"=>"12", "year"=>"2018", "pdf_views"=>"22", "xml_views"=>"0", "html_views"=>"22"}
  • {"month"=>"1", "year"=>"2019", "pdf_views"=>"10", "xml_views"=>"0", "html_views"=>"2"}
  • {"month"=>"2", "year"=>"2019", "pdf_views"=>"4", "xml_views"=>"0", "html_views"=>"1"}
  • {"month"=>"3", "year"=>"2019", "pdf_views"=>"11", "xml_views"=>"0", "html_views"=>"6"}
  • {"month"=>"4", "year"=>"2019", "pdf_views"=>"3", "xml_views"=>"0", "html_views"=>"7"}
  • {"month"=>"5", "year"=>"2019", "pdf_views"=>"3", "xml_views"=>"0", "html_views"=>"4"}
  • {"month"=>"6", "year"=>"2019", "pdf_views"=>"10", "xml_views"=>"0", "html_views"=>"8"}

Figshare

  • {"files"=>["https://ndownloader.figshare.com/files/1587833"], "description"=>"<p>The two predominantly studied STDP learning windows.</p>", "links"=>[], "tags"=>["Computational biology", "computational neuroscience", "Artificial neural networks", "neuroscience", "cognitive science", "artificial intelligence", "Machine learning", "Machine learning algorithms", "Learning and memory", "predominantly", "studied", "stdp"], "article_id"=>1099552, "categories"=>["Biological Sciences"], "users"=>["Joseph Chrol-Cannon", "Yaochu Jin"], "doi"=>"https://dx.doi.org/10.1371/journal.pone.0101792.g011", "stats"=>{"downloads"=>0, "page_views"=>13, "likes"=>0}, "figshare_url"=>"https://figshare.com/articles/_The_two_predominantly_studied_STDP_learning_windows_/1099552", "title"=>"The two predominantly studied STDP learning windows.", "pos_in_sequence"=>0, "defined_type"=>1, "published_date"=>"2014-07-10 03:14:10"}
  • {"files"=>["https://ndownloader.figshare.com/files/1587828"], "description"=>"<p>This indicates the extent that each metric can be used to predict performance.</p>", "links"=>[], "tags"=>["Computational biology", "computational neuroscience", "Artificial neural networks", "neuroscience", "cognitive science", "artificial intelligence", "Machine learning", "Machine learning algorithms", "Learning and memory", "metrics", "simulation", "plotted", "classification"], "article_id"=>1099547, "categories"=>["Biological Sciences"], "users"=>["Joseph Chrol-Cannon", "Yaochu Jin"], "doi"=>"https://dx.doi.org/10.1371/journal.pone.0101792.g007", "stats"=>{"downloads"=>0, "page_views"=>3, "likes"=>0}, "figshare_url"=>"https://figshare.com/articles/_Each_of_the_metrics_for_all_simulation_results_plotted_against_classification_accuracy_in_both_tasks_/1099547", "title"=>"Each of the metrics for all simulation results plotted against classification accuracy in both tasks.", "pos_in_sequence"=>0, "defined_type"=>1, "published_date"=>"2014-07-10 03:14:10"}
  • {"files"=>["https://ndownloader.figshare.com/files/1587836"], "description"=>"<p>Plot of 500 of the 50,000 data samples generated according to Jaeger's time-series benchmark <a href=\"http://www.plosone.org/article/info:doi/10.1371/journal.pone.0101792#pone.0101792-Jaeger4\" target=\"_blank\">[28]</a>.</p>", "links"=>[], "tags"=>["Computational biology", "computational neuroscience", "Artificial neural networks", "neuroscience", "cognitive science", "artificial intelligence", "Machine learning", "Machine learning algorithms", "Learning and memory", "500", "samples", "generated", "time-series", "benchmark"], "article_id"=>1099555, "categories"=>["Biological Sciences"], "users"=>["Joseph Chrol-Cannon", "Yaochu Jin"], "doi"=>"https://dx.doi.org/10.1371/journal.pone.0101792.g012", "stats"=>{"downloads"=>0, "page_views"=>7, "likes"=>0}, "figshare_url"=>"https://figshare.com/articles/_Plot_of_500_of_the_50_000_data_samples_generated_according_to_Jaeger_s_time_series_benchmark_28_/1099555", "title"=>"Plot of 500 of the 50,000 data samples generated according to Jaeger's time-series benchmark [28].", "pos_in_sequence"=>0, "defined_type"=>1, "published_date"=>"2014-07-10 03:14:10"}
  • {"files"=>["https://ndownloader.figshare.com/files/1587813"], "description"=>"<p>Class separation results for 10 initialisations for each combination of plasticity rule, connectivity method and time-series task.</p>", "links"=>[], "tags"=>["Computational biology", "computational neuroscience", "Artificial neural networks", "neuroscience", "cognitive science", "artificial intelligence", "Machine learning", "Machine learning algorithms", "Learning and memory", "10", "initialisations", "plasticity", "connectivity", "time-series"], "article_id"=>1099535, "categories"=>["Biological Sciences"], "users"=>["Joseph Chrol-Cannon", "Yaochu Jin"], "doi"=>"https://dx.doi.org/10.1371/journal.pone.0101792.g002", "stats"=>{"downloads"=>0, "page_views"=>2, "likes"=>0}, "figshare_url"=>"https://figshare.com/articles/_Class_separation_results_for_10_initialisations_for_each_combination_of_plasticity_rule_connectivity_method_and_time_series_task_/1099535", "title"=>"Class separation results for 10 initialisations for each combination of plasticity rule, connectivity method and time-series task.", "pos_in_sequence"=>0, "defined_type"=>1, "published_date"=>"2014-07-10 03:14:10"}
  • {"files"=>["https://ndownloader.figshare.com/files/1587814"], "description"=>"<p>Kernel quality results for 10 initialisations for each combination of plasticity rule, connectivity method and time-series task.</p>", "links"=>[], "tags"=>["Computational biology", "computational neuroscience", "Artificial neural networks", "neuroscience", "cognitive science", "artificial intelligence", "Machine learning", "Machine learning algorithms", "Learning and memory", "10", "initialisations", "plasticity", "connectivity", "time-series"], "article_id"=>1099536, "categories"=>["Biological Sciences"], "users"=>["Joseph Chrol-Cannon", "Yaochu Jin"], "doi"=>"https://dx.doi.org/10.1371/journal.pone.0101792.g003", "stats"=>{"downloads"=>0, "page_views"=>2, "likes"=>0}, "figshare_url"=>"https://figshare.com/articles/_Kernel_quality_results_for_10_initialisations_for_each_combination_of_plasticity_rule_connectivity_method_and_time_series_task_/1099536", "title"=>"Kernel quality results for 10 initialisations for each combination of plasticity rule, connectivity method and time-series task.", "pos_in_sequence"=>0, "defined_type"=>1, "published_date"=>"2014-07-10 03:14:10"}
  • {"files"=>["https://ndownloader.figshare.com/files/1587830"], "description"=>"<p>A uniform connection policy produces variable length chains of connections with some groups of neurons disconnected from others. A scale-free connection policy leads to a structure of a few highly connected hubs and many sparsely connected leaves.</p>", "links"=>[], "tags"=>["Computational biology", "computational neuroscience", "Artificial neural networks", "neuroscience", "cognitive science", "artificial intelligence", "Machine learning", "Machine learning algorithms", "Learning and memory", "types", "connectivity"], "article_id"=>1099549, "categories"=>["Biological Sciences"], "users"=>["Joseph Chrol-Cannon", "Yaochu Jin"], "doi"=>"https://dx.doi.org/10.1371/journal.pone.0101792.g009", "stats"=>{"downloads"=>0, "page_views"=>3, "likes"=>0}, "figshare_url"=>"https://figshare.com/articles/_Illustration_of_two_types_of_connectivity_model_/1099549", "title"=>"Illustration of two types of connectivity model.", "pos_in_sequence"=>0, "defined_type"=>1, "published_date"=>"2014-07-10 03:14:10"}
  • {"files"=>["https://ndownloader.figshare.com/files/1587799"], "description"=>"<p>Classification accuracy results for 10 initialisations for each combination of plasticity rule, connectivity method and time-series task.</p>", "links"=>[], "tags"=>["Computational biology", "computational neuroscience", "Artificial neural networks", "neuroscience", "cognitive science", "artificial intelligence", "Machine learning", "Machine learning algorithms", "Learning and memory", "10", "initialisations", "plasticity", "connectivity", "time-series"], "article_id"=>1099534, "categories"=>["Biological Sciences"], "users"=>["Joseph Chrol-Cannon", "Yaochu Jin"], "doi"=>"https://dx.doi.org/10.1371/journal.pone.0101792.g001", "stats"=>{"downloads"=>0, "page_views"=>2, "likes"=>0}, "figshare_url"=>"https://figshare.com/articles/_Classification_accuracy_results_for_10_initialisations_for_each_combination_of_plasticity_rule_connectivity_method_and_time_series_task_/1099534", "title"=>"Classification accuracy results for 10 initialisations for each combination of plasticity rule, connectivity method and time-series task.", "pos_in_sequence"=>0, "defined_type"=>1, "published_date"=>"2014-07-10 03:14:10"}
  • {"files"=>["https://ndownloader.figshare.com/files/1587829"], "description"=>"<p><b><i>I</i></b> is a multi-dimensional input signal, <b><i>L</i></b> nodes constitute the recurrent reservoir, the <b><i>x</i></b> vector is the reservoir state, <b><i>f</i></b> is the filtering of the spike trains and <b><i>y</i></b> is the output after weight and sum.</p>", "links"=>[], "tags"=>["Computational biology", "computational neuroscience", "Artificial neural networks", "neuroscience", "cognitive science", "artificial intelligence", "Machine learning", "Machine learning algorithms", "Learning and memory", "elements", "reservoir", "computing"], "article_id"=>1099548, "categories"=>["Biological Sciences"], "users"=>["Joseph Chrol-Cannon", "Yaochu Jin"], "doi"=>"https://dx.doi.org/10.1371/journal.pone.0101792.g008", "stats"=>{"downloads"=>3, "page_views"=>8, "likes"=>0}, "figshare_url"=>"https://figshare.com/articles/_Depiction_of_the_elements_of_our_reservoir_computing_model_/1099548", "title"=>"Depiction of the elements of our reservoir computing model.", "pos_in_sequence"=>0, "defined_type"=>1, "published_date"=>"2014-07-10 03:14:10"}
  • {"files"=>["https://ndownloader.figshare.com/files/1587823"], "description"=>"<p>Lyapunov's exponent results plotted against kernel quality in both tasks to show the similarity between the metrics.</p>", "links"=>[], "tags"=>["Computational biology", "computational neuroscience", "Artificial neural networks", "neuroscience", "cognitive science", "artificial intelligence", "Machine learning", "Machine learning algorithms", "Learning and memory", "exponent", "plotted", "kernel", "tasks"], "article_id"=>1099545, "categories"=>["Biological Sciences"], "users"=>["Joseph Chrol-Cannon", "Yaochu Jin"], "doi"=>"https://dx.doi.org/10.1371/journal.pone.0101792.g006", "stats"=>{"downloads"=>1, "page_views"=>2, "likes"=>0}, "figshare_url"=>"https://figshare.com/articles/_Lyapunov_s_exponent_results_plotted_against_kernel_quality_in_both_tasks_to_show_the_similarity_between_the_metrics_/1099545", "title"=>"Lyapunov's exponent results plotted against kernel quality in both tasks to show the similarity between the metrics.", "pos_in_sequence"=>0, "defined_type"=>1, "published_date"=>"2014-07-10 03:14:10"}
  • {"files"=>["https://ndownloader.figshare.com/files/1587821"], "description"=>"<p>Spectral radius results for 10 initialisations for each combination of plasticity rule, connectivity method and time-series task.</p>", "links"=>[], "tags"=>["Computational biology", "computational neuroscience", "Artificial neural networks", "neuroscience", "cognitive science", "artificial intelligence", "Machine learning", "Machine learning algorithms", "Learning and memory", "radius", "10", "initialisations", "plasticity", "connectivity", "time-series"], "article_id"=>1099543, "categories"=>["Biological Sciences"], "users"=>["Joseph Chrol-Cannon", "Yaochu Jin"], "doi"=>"https://dx.doi.org/10.1371/journal.pone.0101792.g005", "stats"=>{"downloads"=>0, "page_views"=>3, "likes"=>0}, "figshare_url"=>"https://figshare.com/articles/_Spectral_radius_results_for_10_initialisations_for_each_combination_of_plasticity_rule_connectivity_method_and_time_series_task_/1099543", "title"=>"Spectral radius results for 10 initialisations for each combination of plasticity rule, connectivity method and time-series task.", "pos_in_sequence"=>0, "defined_type"=>1, "published_date"=>"2014-07-10 03:14:10"}
  • {"files"=>["https://ndownloader.figshare.com/files/1587817"], "description"=>"<p>Lyapunov exponent estimate results for 10 initialisations for each combination of plasticity rule, connectivity method and time-series task.</p>", "links"=>[], "tags"=>["Computational biology", "computational neuroscience", "Artificial neural networks", "neuroscience", "cognitive science", "artificial intelligence", "Machine learning", "Machine learning algorithms", "Learning and memory", "exponent", "10", "initialisations", "plasticity", "connectivity", "time-series"], "article_id"=>1099539, "categories"=>["Biological Sciences"], "users"=>["Joseph Chrol-Cannon", "Yaochu Jin"], "doi"=>"https://dx.doi.org/10.1371/journal.pone.0101792.g004", "stats"=>{"downloads"=>0, "page_views"=>10, "likes"=>0}, "figshare_url"=>"https://figshare.com/articles/_Lyapunov_exponent_estimate_results_for_10_initialisations_for_each_combination_of_plasticity_rule_connectivity_method_and_time_series_task_/1099539", "title"=>"Lyapunov exponent estimate results for 10 initialisations for each combination of plasticity rule, connectivity method and time-series task.", "pos_in_sequence"=>0, "defined_type"=>1, "published_date"=>"2014-07-10 03:14:10"}
  • {"files"=>["https://ndownloader.figshare.com/files/1587839"], "description"=>"<p>Pearson's Correlation between Metrics and Performance.</p>", "links"=>[], "tags"=>["Computational biology", "computational neuroscience", "Artificial neural networks", "neuroscience", "cognitive science", "artificial intelligence", "Machine learning", "Machine learning algorithms", "Learning and memory", "metrics"], "article_id"=>1099556, "categories"=>["Biological Sciences"], "users"=>["Joseph Chrol-Cannon", "Yaochu Jin"], "doi"=>"https://dx.doi.org/10.1371/journal.pone.0101792.t001", "stats"=>{"downloads"=>6, "page_views"=>3, "likes"=>0}, "figshare_url"=>"https://figshare.com/articles/_Pearson_s_Correlation_between_Metrics_and_Performance_/1099556", "title"=>"Pearson's Correlation between Metrics and Performance.", "pos_in_sequence"=>0, "defined_type"=>3, "published_date"=>"2014-07-10 03:14:10"}
  • {"files"=>["https://ndownloader.figshare.com/files/1587832"], "description"=>"<p> is the sliding modification threshold that changes based on a temporal average of post-synaptic activity.</p>", "links"=>[], "tags"=>["Computational biology", "computational neuroscience", "Artificial neural networks", "neuroscience", "cognitive science", "artificial intelligence", "Machine learning", "Machine learning algorithms", "Learning and memory", "bienenstock-cooper-munro", "plasticity", "illustrated", "synaptic", "y-scale", "post-synaptic"], "article_id"=>1099551, "categories"=>["Biological Sciences"], "users"=>["Joseph Chrol-Cannon", "Yaochu Jin"], "doi"=>"https://dx.doi.org/10.1371/journal.pone.0101792.g010", "stats"=>{"downloads"=>1, "page_views"=>72, "likes"=>0}, "figshare_url"=>"https://figshare.com/articles/_The_Bienenstock_Cooper_Munro_plasticity_rule_illustrated_with_synaptic_weight_change_on_the_y_scale_and_post_synaptic_activity_on_the_x_scale_/1099551", "title"=>"The Bienenstock-Cooper-Munro plasticity rule illustrated with synaptic weight change on the y-scale and post-synaptic activity on the x-scale.", "pos_in_sequence"=>0, "defined_type"=>1, "published_date"=>"2014-07-10 03:14:10"}

PMC Usage Stats | Further Information

  • {"unique-ip"=>"7", "full-text"=>"7", "pdf"=>"2", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2015", "month"=>"4"}
  • {"unique-ip"=>"7", "full-text"=>"8", "pdf"=>"2", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2015", "month"=>"5"}
  • {"unique-ip"=>"3", "full-text"=>"3", "pdf"=>"3", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2015", "month"=>"6"}
  • {"unique-ip"=>"8", "full-text"=>"10", "pdf"=>"1", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2015", "month"=>"7"}
  • {"unique-ip"=>"5", "full-text"=>"5", "pdf"=>"1", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"1", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2015", "month"=>"3"}
  • {"unique-ip"=>"4", "full-text"=>"4", "pdf"=>"0", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"1", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2015", "month"=>"2"}
  • {"unique-ip"=>"9", "full-text"=>"8", "pdf"=>"1", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2015", "month"=>"8"}
  • {"unique-ip"=>"6", "full-text"=>"5", "pdf"=>"0", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2015", "month"=>"9"}
  • {"unique-ip"=>"7", "full-text"=>"6", "pdf"=>"0", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"1", "year"=>"2015", "month"=>"10"}
  • {"unique-ip"=>"4", "full-text"=>"3", "pdf"=>"1", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2014", "month"=>"7"}
  • {"unique-ip"=>"4", "full-text"=>"1", "pdf"=>"2", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"2", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2014", "month"=>"8"}
  • {"unique-ip"=>"8", "full-text"=>"2", "pdf"=>"2", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"4", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2014", "month"=>"9"}
  • {"unique-ip"=>"3", "full-text"=>"2", "pdf"=>"1", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"1", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2014", "month"=>"10"}
  • {"unique-ip"=>"1", "full-text"=>"2", "pdf"=>"0", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2016", "month"=>"2"}
  • {"unique-ip"=>"3", "full-text"=>"3", "pdf"=>"0", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"1", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2014", "month"=>"11"}
  • {"unique-ip"=>"4", "full-text"=>"2", "pdf"=>"2", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2014", "month"=>"12"}
  • {"unique-ip"=>"13", "full-text"=>"6", "pdf"=>"7", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"4", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2015", "month"=>"11"}
  • {"unique-ip"=>"9", "full-text"=>"7", "pdf"=>"2", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2015", "month"=>"12"}
  • {"unique-ip"=>"2", "full-text"=>"1", "pdf"=>"1", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2016", "month"=>"1"}
  • {"unique-ip"=>"1", "full-text"=>"2", "pdf"=>"0", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2016", "month"=>"3"}
  • {"unique-ip"=>"5", "full-text"=>"3", "pdf"=>"1", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"2", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2016", "month"=>"4"}
  • {"unique-ip"=>"1", "full-text"=>"0", "pdf"=>"0", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"1", "year"=>"2016", "month"=>"5"}
  • {"unique-ip"=>"2", "full-text"=>"0", "pdf"=>"3", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2016", "month"=>"6"}
  • {"unique-ip"=>"5", "full-text"=>"3", "pdf"=>"1", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"1", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2016", "month"=>"7"}
  • {"unique-ip"=>"2", "full-text"=>"0", "pdf"=>"0", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"2", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2016", "month"=>"8"}
  • {"unique-ip"=>"1", "full-text"=>"1", "pdf"=>"0", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"1", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2016", "month"=>"9"}
  • {"unique-ip"=>"3", "full-text"=>"2", "pdf"=>"1", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2016", "month"=>"10"}
  • {"unique-ip"=>"2", "full-text"=>"2", "pdf"=>"1", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2016", "month"=>"11"}
  • {"unique-ip"=>"2", "full-text"=>"3", "pdf"=>"0", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2016", "month"=>"12"}
  • {"unique-ip"=>"4", "full-text"=>"3", "pdf"=>"1", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2017", "month"=>"1"}
  • {"unique-ip"=>"3", "full-text"=>"3", "pdf"=>"0", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2017", "month"=>"2"}
  • {"unique-ip"=>"1", "full-text"=>"1", "pdf"=>"0", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2017", "month"=>"3"}
  • {"unique-ip"=>"2", "full-text"=>"2", "pdf"=>"0", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2017", "month"=>"4"}
  • {"unique-ip"=>"4", "full-text"=>"4", "pdf"=>"1", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2017", "month"=>"5"}
  • {"unique-ip"=>"2", "full-text"=>"3", "pdf"=>"3", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2017", "month"=>"6"}
  • {"unique-ip"=>"5", "full-text"=>"5", "pdf"=>"1", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2017", "month"=>"7"}
  • {"unique-ip"=>"3", "full-text"=>"3", "pdf"=>"2", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2017", "month"=>"8"}
  • {"unique-ip"=>"3", "full-text"=>"2", "pdf"=>"1", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2017", "month"=>"9"}
  • {"unique-ip"=>"3", "full-text"=>"2", "pdf"=>"1", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2017", "month"=>"10"}
  • {"unique-ip"=>"4", "full-text"=>"5", "pdf"=>"0", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"2", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2017", "month"=>"11"}
  • {"unique-ip"=>"3", "full-text"=>"3", "pdf"=>"0", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2018", "month"=>"1"}
  • {"unique-ip"=>"2", "full-text"=>"3", "pdf"=>"0", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2018", "month"=>"3"}
  • {"unique-ip"=>"4", "full-text"=>"5", "pdf"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2019", "month"=>"1"}
  • {"unique-ip"=>"10", "full-text"=>"10", "pdf"=>"3", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"1", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2018", "month"=>"12"}
  • {"unique-ip"=>"5", "full-text"=>"1", "pdf"=>"8", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"1", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2018", "month"=>"11"}
  • {"unique-ip"=>"7", "full-text"=>"6", "pdf"=>"1", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"1", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2018", "month"=>"9"}
  • {"unique-ip"=>"16", "full-text"=>"25", "pdf"=>"7", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2018", "month"=>"4"}
  • {"unique-ip"=>"3", "full-text"=>"3", "pdf"=>"2", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2018", "month"=>"5"}
  • {"unique-ip"=>"4", "full-text"=>"5", "pdf"=>"2", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2018", "month"=>"6"}
  • {"unique-ip"=>"8", "full-text"=>"7", "pdf"=>"1", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2018", "month"=>"7"}
  • {"unique-ip"=>"10", "full-text"=>"8", "pdf"=>"1", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"2", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2018", "month"=>"10"}
  • {"unique-ip"=>"6", "full-text"=>"6", "pdf"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2018", "month"=>"8"}
  • {"unique-ip"=>"9", "full-text"=>"9", "pdf"=>"3", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2019", "month"=>"2"}
  • {"unique-ip"=>"9", "full-text"=>"8", "pdf"=>"3", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2019", "month"=>"3"}
  • {"unique-ip"=>"6", "full-text"=>"4", "pdf"=>"4", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2019", "month"=>"4"}
  • {"unique-ip"=>"5", "full-text"=>"4", "pdf"=>"1", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2019", "month"=>"5"}

Relative Metric

{"start_date"=>"2014-01-01T00:00:00Z", "end_date"=>"2014-12-31T00:00:00Z", "subject_areas"=>[{"subject_area"=>"/Biology and life sciences", "average_usage"=>[291]}, {"subject_area"=>"/Engineering and technology", "average_usage"=>[282]}, {"subject_area"=>"/Engineering and technology/Signal processing", "average_usage"=>[276]}, {"subject_area"=>"/Physical sciences/Mathematics", "average_usage"=>[286]}, {"subject_area"=>"/Physical sciences/Physics", "average_usage"=>[266]}]}
Loading … Spinner
There are currently no alerts