-
Nonlinear decoding of a complex movie from the mammalian retina
This package contains data for the publication "Nonlinear decoding of a complex movie from the mammalian retina" by Deny S. et al, PLOS Comput Biol (2018). The data consists of... -
A prediction rigidity formalism for low-cost uncertainties in trained neural ...
Quantifying the uncertainty of regression models is essential to ensure their reliability, particularly since their application often extends beyond their training domain. Based... -
Underwater camera photos with manual tagging of fish species at OBSEA seafloo...
Underwater images and manual tags of different fish taxa detected from the image repository of the OBSEA Cabled Observatory from January 2013 to December 2014. OBSEA station is... -
A new dataset of satellite observation-based global surface soil moisture cov...
Soil moisture is an important variable linking the atmosphere and the terrestrial ecosystems. However, long-term satellite monitoring of surface soil moisture is still lacking... -
Nonlinear decoding of a complex movie from the mammalian retina
This package contains data for the publication "Nonlinear decoding of a complex movie from the mammalian retina" by Deny S. et al, PLOS Comput Biol (2018). The data consists of... -
Replication Data for: A neural network model for the evolution of learning in...
This dataset includes the simulation code in c++, an executable file (for Windows), an example of the parameter file, example output data with the corresponding parameter file,... -
On double-descent in uncertainty quantification in overparametrized models (c...
Uncertainty quantification is a central challenge in reliable and trustworthy machine learning. Naive measures such as last-layer scores are well-known to yield overconfident... -
Expectation consistency for calibration of neural networks (code)
Despite their incredible performance, it is well reported that deep neural networks tend to be overoptimistic about their prediction confidence. Finding effective and efficient... -
Character-level part-of-speech tagger of Slovene language
Part-of-speech tagger for Slovene language implemented using convolutional and LSTM neural networks. Tagger uses character-level representation of sentences. The tagger has been... -
PyTorch model for Slovenian Coreference Resolution
Slovenian model for coreference resolution: a neural network based on a customized transformer architecture, usable with the code published on... -
Czech image captioning, machine translation, and sentiment analysis (Neural M...
This submission contains trained end-to-end models for the Neural Monkey toolkit for Czech and English, solving three NLP tasks: machine translation, image captioning, and... -
Czech image captioning, machine translation, sentiment analysis and summariza...
This submission contains trained end-to-end models for the Neural Monkey toolkit for Czech and English, solving four NLP tasks: machine translation, image captioning, sentiment... -
Recurrent conditional heteroskedasticity (replication data)
We propose a new class of financial volatility models, called the REcurrent Conditional Heteroskedastic (RECH) models, to improve both in-sample analysis and out-of-sample... -
Disentangling the complexity of tropical small-scale fisheries dynamics using...
Data serie of small-scale fisheries of San Pedro port, Tabasco, México. These data are kg/fishery trip (lines) by species (common name, columns), by gear type year and month.... -
Viscosity in water from first-principles and deep-neural-network simulations
We report on an extensive study of the viscosity of liquid water at near-ambient conditions, performed within the Green-Kubo theory of linear response and equilibrium ab initio... -
Properties of α-brass nanoparticles. 1. Neural network potential energy surface
Data for Properties of α-Brass Nanoparticles. 1. Neural Network Potential Energy Surface Jan Weinreich, Anton Römer, Martín Leandro Paleico, and Jörg Behler 53 841 reference... -
Viscosity in water from first-principles and deep-neural-network simulations
We report on an extensive study of the viscosity of liquid water at near-ambient conditions, performed within the Green-Kubo theory of linear response and equilibrium ab initio... -
Graph Dynamical Networks for Unsupervised Learning of Atomic Scale Dynamics i...
Understanding the dynamical processes that govern the performance of functional materials is essential for the design of next generation materials to tackle global energy and... -
Accelerating Finite-temperature Kohn-Sham Density Functional Theory with Deep...
Output from electronic structure code (Quantum Espresso) that serves as training data for the machine-learning workflow of the related scientific publication... -
Electron density derived with the Neural-network-based Upper-hybrid Resonance...
The dataset presents the electron density derived using the Neural-network-based Upper hybrid Resonance Determination (NURD) algorithm (Zhelavskaya et al., 2016) from plasma...