No packages match

rnn - Recurrent Neural Network

Implementation of a Recurrent Neural Network architectures in native R, including Long Short-Term Memory (Hochreiter and Schmidhuber, <doi:10.1162/neco.1997.9.8.1735>), Gated Recurrent Unit (Chung et al.) and vanilla RNN.

Last updated

7.64 score 76 stars 82 scripts 588 downloads

decompr - Global Value Chain Decomposition

Four global value chain (GVC) decompositions are implemented. The Leontief decomposition derives the value added origin of exports by country and industry as in Hummels, Ishii and Yi (2001). The Koopman, Wang and Wei (2014) decomposition splits country-level exports into 9 value added components, and the Wang, Wei and Zhu (2013) decomposition splits bilateral exports into 16 value added components. The Borin and Mancini (2019) decomposition splits country-, sector- or bilateral-level exports into up to 13 value added and GVC components. Various GVC indicators based on these decompositions are computed in the complimentary 'gvc' package. --- References: --- Hummels, D., Ishii, J., & Yi, K. M. (2001). The nature and growth of vertical specialization in world trade. Journal of international Economics, 54(1), 75-96. Koopman, R., Wang, Z., & Wei, S. J. (2014). Tracing value-added and double counting in gross exports. American Economic Review, 104(2), 459-94. Wang, Z., Wei, S. J., & Zhu, K. (2013). Quantifying international production sharing at the bilateral and sector levels (No. w19677). National Bureau of Economic Research. Borin, A., & Mancini, M. (2019). Measuring What Matters in Global Value Chains and Value-Added Trade. World Bank Policy Research Working Paper 8804.

Last updated

6.92 score 20 stars 1 dependents 139 scripts 690 downloads

diagonals - Block Diagonal Extraction or Replacement

Several tools for handling block-matrix diagonals and similar constructs are implemented. Block-diagonal matrices can be extracted or removed using two small functions implemented here. In addition, non-square matrices are supported. Block diagonal matrices occur when two dimensions of a data set are combined along one edge of a matrix. For example, trade-flow data in the 'decompr' and 'gvc' packages have each country-industry combination occur along both edges of the matrix.

Last updated

6.10 score 2 stars 7 dependents 45 scripts 1.3k downloads

HomomorphicEncryption - BFV, BGV, CKKS Schema for Fully Homomorphic Encryption

Implements the Brakerski-Fan-Vercauteren (BFV, 2012) <https://eprint.iacr.org/2012/144>, Brakerski-Gentry-Vaikuntanathan (BGV, 2014) <doi:10.1145/2633600>, and Cheon-Kim-Kim-Song (CKKS, 2016) <https://eprint.iacr.org/2016/421.pdf> schema for Fully Homomorphic Encryption. The included vignettes demonstrate the encryption procedures.

Last updated

5.97 score 1 stars 109 scripts 379 downloads

gvc - Global Value Chains Tools

Several tools for Global Value Chain ('GVC') analysis are implemented.

Last updated

5.80 score 24 stars 52 scripts 524 downloads

sigmoid - Sigmoid Functions for Machine Learning

Several different sigmoid functions are implemented, including a wrapper function, SoftMax preprocessing and inverse functions.

Last updated

5.66 score 2 stars 1 dependents 151 scripts 472 downloads

rddtools - Toolbox for Regression Discontinuity Design ('RDD')

Set of functions for Regression Discontinuity Design ('RDD'), for data visualisation, estimation and testing.

Last updated

5.64 score 11 stars 6 scripts 464 downloads

attention - Self-Attention Algorithm

Self-Attention algorithm helper functions and demonstration vignettes of increasing depth on how to construct the Self-Attention algorithm, this is based on Vaswani et al. (2017) <doi:10.48550/arXiv.1706.03762>, Dan Jurafsky and James H. Martin (2022, ISBN:978-0131873216) <https://web.stanford.edu/~jurafsky/slp3/> "Speech and Language Processing (3rd ed.)" and Alex Graves (2020) <https://www.youtube.com/watch?v=AIiwuClvH6k> "Attention and Memory in Deep Learning".

Last updated

5.26 score 2 stars 3 dependents 10 scripts 497 downloads

transformer - Implementation of Transformer Deep Neural Network with Vignettes

Transformer is a Deep Neural Network Architecture based i.a. on the Attention mechanism (Vaswani et al. (2017) <doi:10.48550/arXiv.1706.03762>).

Last updated

4.96 score 1 stars 2 dependents 304 scripts 255 downloads

locpol - Kernel Local Polynomial Regression

Computes local polynomial estimators for the regression and also density. It comprises several different utilities to handle kernel estimators.

Last updated

4.76 score 1 stars 10 dependents 194 scripts 928 downloads

datasets.load - Graphical Interface for Loading Datasets

Graphical interface for loading datasets in RStudio from all installed (including unloaded) packages, also includes command line interfaces.

Last updated

3.48 score 5 stars 12 scripts 493 downloads

HEtools - Homomorphic Encryption Polynomials

Homomorphic encryption (Brakerski and Vaikuntanathan (2014) <doi:10.1137/120868669>) using Ring Learning with Errors (Lyubashevsky et al. (2012) <https://eprint.iacr.org/2012/230>) is a form of Learning with Errors (Regev (2005) <doi:10.1145/1060590.1060603>) using polynomial rings over finite fields. Functions to generate the required polynomials (using 'polynom'), with various distributions of coefficients are provided. Additionally, functions to generate and take coefficient modulo are provided.

Last updated

3.18 score 1 stars 1 dependents 2 scripts 262 downloads