Package: reservoirnet 0.2.0
reservoirnet: Reservoir Computing and Echo State Networks
A simple user-friendly library based on the 'python' module 'reservoirpy'. It provides a flexible interface to implement efficient Reservoir Computing (RC) architectures with a particular focus on Echo State Networks (ESN). Some of its features are: offline and online training, parallel implementation, sparse matrix computation, fast spectral initialization, advanced learning rules (e.g. Intrinsic Plasticity) etc. It also makes possible to easily create complex architectures with multiple reservoirs (e.g. deep reservoirs), readouts, and complex feedback loops. Moreover, graphical tools are included to easily explore hyperparameters. Finally, it includes several tutorials exploring time series forecasting, classification and hyperparameter tuning. For more information about 'reservoirpy', please see Trouvain et al. (2020) <doi:10.1007/978-3-030-61616-8_40>. This package was developed in the framework of the University of Bordeaux’s IdEx "Investments for the Future" program / RRI PHDS.
Authors:
reservoirnet_0.2.0.tar.gz
reservoirnet_0.2.0.zip(r-4.5)reservoirnet_0.2.0.zip(r-4.4)reservoirnet_0.2.0.zip(r-4.3)
reservoirnet_0.2.0.tgz(r-4.4-any)reservoirnet_0.2.0.tgz(r-4.3-any)
reservoirnet_0.2.0.tar.gz(r-4.5-noble)reservoirnet_0.2.0.tar.gz(r-4.4-noble)
reservoirnet_0.2.0.tgz(r-4.4-emscripten)reservoirnet_0.2.0.tgz(r-4.3-emscripten)
reservoirnet.pdf |reservoirnet.html✨
reservoirnet/json (API)
# Install 'reservoirnet' in R: |
install.packages('reservoirnet', repos = c('https://thomasferte.r-universe.dev', 'https://cloud.r-project.org')) |
- dfCovid - Datagouv covid-19 dataset
This package does not link to any Github/Gitlab/R-forge repository. No issue tracker or development information is available.
Last updated 2 years agofrom:70e064ea45. Checks:OK: 7. Indexed: yes.
Target | Result | Date |
---|---|---|
Doc / Vignettes | OK | Oct 26 2024 |
R-4.5-win | OK | Oct 26 2024 |
R-4.5-linux | OK | Oct 26 2024 |
R-4.4-win | OK | Oct 26 2024 |
R-4.4-mac | OK | Oct 26 2024 |
R-4.3-win | OK | Oct 26 2024 |
R-4.3-mac | OK | Oct 26 2024 |
Exports:%>>%createNodegenerate_datainstall_reservoirpylinkplot_2x2_perfplot_marginal_perfplot_perf_22predict_seqrandom_search_hyperparamreservoirR_fitrloguniform
Dependencies:abindbackportsbootbriobroomcallrcarcarDataclicolorspacecorrplotcowplotcpp11crayonDerivdescdiffobjdigestdoBydplyrevaluatefansifarverFormulafsgenericsggplot2ggpubrggrepelggsciggsignifgluegridExtragtableherehmsisobandjanitorjsonlitelabelinglatticelifecyclelme4lubridatemagrittrMASSMatrixMatrixModelsmgcvmicrobenchmarkminqamodelrmunsellnlmenloptrnnetnumDerivpbkrtestpillarpkgbuildpkgconfigpkgloadpngpolynompraiseprocessxpspurrrquantregR6rappdirsRColorBrewerRcppRcppEigenRcppTOMLrematch2reticulaterlangrprojrootrstatixscalessnakecaseSparseMstringistringrsurvivaltestthattibbletidyrtidyselecttimechangeutf8vctrsviridisLitewaldowithr
01 - The basics first, you should learn
Rendered frombasic_usage_01.Rmd
usingknitr::rmarkdown
on Oct 26 2024.Last update: 2023-04-04
Started: 2023-04-04
02 - Hyperparameter tuning with random search
Rendered fromhyperparameter_tuning_02.Rmd
usingknitr::rmarkdown
on Oct 26 2024.Last update: 2023-04-04
Started: 2023-04-04
Classification with Reservoir Computing
Rendered fromClassification_with_RC.Rmd
usingknitr::rmarkdown
on Oct 26 2024.Last update: 2023-04-04
Started: 2023-04-04
Readme and manuals
Help Manual
Help page | Topics |
---|---|
Takes two nodes and applies python operator '>>' | %>>% chevron |
Function to create some node | createNode |
Datagouv covid-19 dataset | dfCovid |
Load data from the 'Japanese vowels' or the 'Mackey-Glass' | generate_data |
Install reservoirpy | install_reservoirpy |
Link two :py:class:'~.Node' instances to form a :py:class:'~.Model' instance. 'node1' output will be used as input for 'node2' in the created model. This is similar to a function composition operation: | link |
plot_2x2_perf | plot_2x2_perf |
plot_marginal_perf | plot_marginal_perf |
plot_perf_22 | plot_perf_22 |
plot.reservoir_predict_seq | plot.reservoir_predict_seq |
Run the node-forward function on a sequence of data | predict_seq |
reservoirR_fit print summary | print.summary.reservoirR_fit |
random_search_hyperparam | random_search_hyperparam |
Offline fitting method of a Node | reservoirR_fit |
rloguniform | rloguniform |
summary.reservoir_predict_seq | summary.reservoir_predict_seq |
reservoirR_fit summary | summary.reservoirR_fit |