cito: An R package for training neural networks using torch

Domaine:

environment and energy

Type de record:

papersoftware

Créateur:

AmeHarPic

Hôte:

Deep Neural Networks (DNN) have become a central method in ecology. Most current deep learning (DL) applications rely on one of the major deep learning frameworks, in particular Torch or TensorFlow, to build and train DNN. Using these frameworks, however, requires substantially more experience and time than typical regression functions in the R environment. Here, we present 'cito', a user-friendly R package for DL that allows specifying DNNs in the familiar formula syntax used by many R packages. To fit the models, 'cito' uses 'torch', taking advantage of the numerically optimized torch library, including the ability to switch between training models on the CPU or the graphics processing unit (GPU) (which allows to efficiently train large DNN). Moreover, 'cito' includes many user-friendly functions for model plotting and analysis, including optional confidence intervals (CIs) based on bootstraps for predictions and explainable AI (xAI) metrics for effect sizes and variable importance with CIs and p-values. To showcase a typical analysis pipeline using 'cito', including its built-in xAI features to explore the trained DNN, we build a species distribution model of the African elephant. We hope that by providing a user-friendly R framework to specify, deploy and interpret DNN, 'cito' will make this interesting model class more accessible to ecological data analysis. A stable version of 'cito' can be installed from the comprehensive R archive network (CRAN). 12 pages, 4 figures, 2 tables

Visit

arxiv.org

Similaires

Harmful Insects Detection Using Convolutional Neural Networks (Faster R-CNN) *sits, an open-source R package for satellite image time series analysis using machine learninggeohabnet: An R package for mapping habitat connectivity for biosecurity and conservationBuilding Word Representations for Wolof Using Neural NetworksSPODT: An R Package to Perform Spatial PartitioningAn R package to work with Ethiopian dates

Harmful Insects Detection Using Convolutional Neural Networks (Faster R-CNN) *

International audience Insect detection is a crucial task in various fields, includin

sits, an open-source R package for satellite image time series analysis using machine learning

Gilberto Câmara is part of the INPE, the National Institute for Space Research. In his talk, Gilbert

geohabnet: An R package for mapping habitat connectivity for biosecurity and conservation

Mapping habitat suitability, based on factors like host availability and environmental suitability,

Building Word Representations for Wolof Using Neural Networks

SPODT: An R Package to Perform Spatial Partitioning

International audience Spatial cluster detection is a classical question in epidemiol

An R package to work with Ethiopian dates

A robust and efficient solution for working with Ethiopian dates. It can seamlessly convert to and f