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
7.63 score 77 stars 79 scripts 692 downloadsrddtools - Toolbox for Regression Discontinuity Design ('RDD')
Set of functions for Regression Discontinuity Design ('RDD'), for data visualisation, estimation and testing.
Last updated
7.33 score 11 stars 193 scripts 561 downloadsdiagonals - 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
6.09 score 2 stars 9 dependents 39 scripts 1.2k downloadssigmoid - Sigmoid Functions for Machine Learning
Several different sigmoid functions are implemented, including a wrapper function, SoftMax preprocessing and inverse functions.
Last updated
5.77 score 2 stars 1 dependents 195 scripts 777 downloadsgvc - Global Value Chains Tools
Several tools for Global Value Chain ('GVC') analysis are implemented.
Last updated
5.69 score 22 stars 45 scripts 286 downloadsHomomorphicEncryption - 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
5.52 score 1 stars 39 scripts 154 downloadsattention - 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 6 scripts 411 downloadslocpol - 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
4.97 score 1 stars 10 dependents 182 scripts 1.7k downloadstransformer - 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
4.76 score 1 stars 2 dependents 190 scripts 163 downloadsdatasets.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
3.40 score 5 stars 10 scripts 373 downloadsHEtools - 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 167 downloads