Find research datasets worth reusing
Search datasets from major research repositories and use ShareScore to quickly assess how well each record supports discovery, access, and reuse.
921
datasets available to search
ShareScore release 0.7.1
Dataset results
921 results for “Neural Network”
Data set for "Low-Power Artificial Neural Network Perceptron Based on Monolayer MoS2"
<p>Data sets for the publication "Low-Power Artificial Neural Network Perceptron Based on Monolayer MoS<sub>2</sub>", doi:10.1021/acsnano.1c07065</p>
Cortical oscillations support sampling-based computations in spiking neural networks
<p>This archive contains the scripts for generating the data and figures and the data of the publication: "Cortical oscillations support sampling-based computations in spiking neural networks".</p> <p>The different parts of the material are grouped into separate archives to enable modular usage and can be individually downloaded as required:</p> <ul> <li>The archive spike-based-tempering_scripts.tgz contains all the scripts to reproduce the simulation data and figures.</li> <li>The file software.img contains the third-party software needed to execute the simulations of the current-based experiments.</li> <li>The archive current-based_experiments_data includes the scripts and the simulation data for the current-based experiments.</li> </ul>
Automatic taxonomic identification based on the Fossil Image Dataset (>415,000 images) and deep convolutional neural networks
<p>This is a Fossil Image Dataset, which contains >415000 images. A total of 50 clades were labeled, with a final 90% accuracy. We used the web crawler to download fossil images from the Internet. We declare that all the collected images are used for academic purposes only. If anyone wants to use this dataset, please agree on the Terms of access for the Fossil Image Dataset (FID). We uploaded two datasets: FID (contains 0.415 million images) and reduced-FID (60 thousand images, 1200 for each clade). Requirements of necessary preinstalled Python libraries, algorithms for analysis, and the model weights are available at <a href="https://github.com/XiaokangLiuCUG/Fossil_Image_Dataset">https://github.com/XiaokangLiuCUG/Fossil_Image_Dataset</a>.</p>
Convolutional Neural Networks for LPV-Approximations of Semi-discrete Navier-Stokes Equations
<pre><code>A `python` module with * a dynamic setup of *Convolutional Neural Networks* in `PyTorch` * an interface to `FEniCS` to generate data from FEM simulations of flows and * a numerical realization of FEM norm in the training neural networks developed to design very low-dimensional LPV approximations of incompressible Navier-Stokes equations.</code></pre> <p> </p> <p><code>These files contain the core module </code>and the scripts that produce the numerical examples of the paper with <a href="https://doi.org/10.3389/fams.2022.879140">doi:10.3389/fams.2022.879140</a></p> <p> </p> <pre><code>> Benner, Heiland, Bahmani (2022): *Convolutional Neural Networks for Very Low-dimensional LPV Approximations of Incompressible Navier-Stokes Equations* </code></pre> <p> </p>
A Deep Neural Network Based SMAP Soil Moisture Product
<p>It is demonstrated that while satellite soil moisture (SM) retrievals often have minimum biases, reanalysis data can capture more temporal variability of SM, especially for non-cropland areas -- when validated against in situ measurements. Accordingly, this paper presents a deep neural network (DNN) that utilizes the merits of a suite of existing satellite and reanalysis products to produce a new SM product with minimum (maximum) bias (correlation) -- using NASA’s Soil Moisture Active Passive (SMAP) data and ERA5 reanalysis. The benchmark of the network is a bias-adjusted SM with maximum correlation with in situ data over each land-cover type. The mean of the benchmark data is adjusted to the product that exhibits a minimum bias over each land-cover type. Consistent with the laws of L-band microwave propagation in soil and canopy, the input variables of DNN include polarized SMAP brightness temperatures, incidence angle, vegetation scattering albedo, surface roughness parameter, surface water fraction, effective soil temperatures, bulk density, clay fraction, and vegetation optical depth from the normalized difference vegetation index (NDVI) climatology. The DNN is trained and validated using two years (04/2015--03/2017) of global data and deployed for assessment of its performance from 04/2017 to 03/2021. The testing results against in situ measurements demonstrate that the DNN outputs typically exhibit improved error quality metrics over most land-cover types and climate regimes and can properly capture SM temporal dynamics, beyond each SMAP product across regional to continental scales.</p>
A tempοral Deep Convolutional Neural Network model on Sentinel-1 Image Time Series for pixel-wise Flood Classification (dataset)
<p>This is a dataset which has been designed to be used for flood time series classification. Each time series is annotated as flood or no-flood and represents a pixel-wise time series derived from stack of Sentinel-1 IW GRD images that have been pre-processed according to <a href="http://doi.org/10.5281/zenodo.6510223">https://doi.org/10.5281/zenodo.6510223</a>.</p>
Neural-network-backed evolutionary search for SrTiO3(110) surface reconstructions
<p>The archive "dataset.tar.gz" contains trained models (neural networks), training-, validation- and test-data and selected structures in POSCAR format, obtained in the neural-network-backed evolutionary search for SrTiO3(110) surface reconstructions.</p> <p>See README for more information on the archive content.</p>
Image sensing with multilayer, nonlinear optical neural networks
<p>This data repository contains the information necessary to reproduce the main results of the paper “Image sensing with multiplayer, nonlinear optical neural networks”.</p> <p>This repository contains the data and the code for generating the figures in the manuscript "Image sensing with multilayer, nonlinear optical neural networks", including figures in the main text and in supplementary materials. The repository also contains the code for controling the experiment setup and running the experiments conducted in the paper:</p> <ul> <li>Folder 'Data_Collection_Example' and 'Data_Extraction_Example' contain example scripts for instrument control and data collection using the multilayer optical-neural-network sensor.</li> <li>Other folders are organized according to the figure panels in the main text, each containing the data and the code required to reproduce the plots in a main figure panel and its associated supplementary figures. In each of these folders, there is a README.txt file that summarizes the role of each file in the folder. </li> </ul>
Global Positioning System Based on Optical Flow and Convolutional Neural Network
<p>Two datasets used in the paper Global Positioning System Based on Optical Flow and Convolutional Neural Network, to evaluate the proposed CNN model to the task of position estimation. The datasets cover 2 different modes of motion of a drone, and were captured using Google API.</p>
Sparsified Model Zoo Twins: A Dataset of Sparsified Populations of Neural Network Models - MNIST
<p><strong>Abstract</strong></p> <p>In the last years, neural networks have evolved from laboratory environments to the state-of-the-art for many real-world problems. Our hypothesis is that neural network models (i.e., their weights and biases) evolve on unique, smooth trajectories in weight space during training. Following, a population of such neural network models (refereed to as “model zoo”) would form topological structures in weight space. We think that the geometry, curvature and smoothness of these structures contain information about the state of training and can be reveal latent properties of individual models. With such zoos, one could investigate novel approaches for (i) model analysis, (ii) discover unknown learning dynamics, (iii) learn rich representations of such populations, or (iv) exploit the model zoos for generative modelling of neural network weights and biases. Unfortunately, the lack of standardized model zoos and available benchmarks significantly increases the friction for further research about populations of neural networks. With this work, we publish a novel dataset of model zoos containing systematically generated and diverse populations of neural network models for further research. In total the proposed model zoo dataset is based on six image datasets, consist of 27 model zoos with varying hyperparameter combinations are generated and includes 50’360 unique neural network models resulting in over 2’585’360 collected model states. Additionally, to the model zoo data we provide an in-depth analysis of the zoos and provide benchmarks for multiple downstream tasks as mentioned before.</p> <p><strong>Dataset</strong></p> <p>This dataset is part of a larger collection of model zoos and contains the sparsified twins of models trained on MNIST. The original population is made available at https://doi.org/10.5281/zenodo.6632086. Sparsification is done using Variational Dropout, starting from the last epoch of the original population. The zip file contains the sparsification trajectory for 25 epochs for all 1000 models. All zoos with extensive information and code can be found at www.modelzoos.cc.</p> <p> </p>
Sparsified Model Zoo Twins: A Dataset of Sparsified Populations of Neural Network Models - SVHN
<p><strong>Abstract</strong></p> <p>In the last years, neural networks have evolved from laboratory environments to the state-of-the-art for many real-world problems. Our hypothesis is that neural network models (i.e., their weights and biases) evolve on unique, smooth trajectories in weight space during training. Following, a population of such neural network models (refereed to as “model zoo”) would form topological structures in weight space. We think that the geometry, curvature and smoothness of these structures contain information about the state of training and can be reveal latent properties of individual models. With such zoos, one could investigate novel approaches for (i) model analysis, (ii) discover unknown learning dynamics, (iii) learn rich representations of such populations, or (iv) exploit the model zoos for generative modelling of neural network weights and biases. Unfortunately, the lack of standardized model zoos and available benchmarks significantly increases the friction for further research about populations of neural networks. With this work, we publish a novel dataset of model zoos containing systematically generated and diverse populations of neural network models for further research. In total the proposed model zoo dataset is based on six image datasets, consist of 27 model zoos with varying hyperparameter combinations are generated and includes 50’360 unique neural network models resulting in over 2’585’360 collected model states. Additionally, to the model zoo data we provide an in-depth analysis of the zoos and provide benchmarks for multiple downstream tasks as mentioned before.</p> <p><strong>Dataset</strong></p> <p>This dataset is part of a larger collection of model zoos and contains the sparsified twins of models trained on SVHN. The original population is made available at https://doi.org/10.5281/zenodo.6632120. Sparsification is done using Variational Dropout, starting from the last epoch of the original population. The zip file contains the sparsification trajectory for 25 epochs for all 1000 models. All zoos with extensive information and code can be found at www.modelzoos.cc.</p>
Global sea surface dimethyl sulfide dataset simulated by artificial neural network
<p>This dataset contains (1) the matched and binned data used for constructing an artificial neural network (ANN) model to simulate the sea surface concentration of dimethyl sulfide (DMS); (2) the simulated global daily sea surface concentrations of DMS ranging from 2005 to 2014 by ANN model and the calculated total transfer velocities (Kt) and sea-to-air fluxes; (3) the simulated global monthly sea surface concentrations of DMS ranging from 2005 to 2100 by ANN model and CMIP6 ensemble and the calculated Kt and sea-to-air fluxes; (4) the yearly mean DMS concentration of each grid in different sensitivity experiments exploring the roles different variables play in driving DMS future changes. The input variables of this ANN model include chlorophyll <em>a</em>, sea surface temperature (SST), mixed layer depth (MLD), nitrate, phosphate, silicate, dissolved oxygen (DO), downward short-wave radiation (DSWF), and sea surface salinity (SSS). The future projections (2015-2100) are subjected into two Shared Socioeconomic Pathway scenarios SSP2-4.5 and SSP5-8.5. The spatial resolution of the simulated dataset is 1°×1°. The units of DMS concentration, Kt, and flux are nmol L<sup>–1</sup>, m s<sup>–1</sup>, and μmol S m<sup>–2</sup> d <sup>–1</sup>, respectively.</p> <p>Compared with the previous version (v1.0), this version is based on an updated ANN model after adjusting the data match-up between satellite and in-situ chlorophyll <em>a</em> for ANN training. In addition, the historical simulation based on CMIP6 only covers the time period from 2005 to 2014, which was from 1850 to 2014 for v1.0.</p>
Data From: Emulation of Cardiac Mechanics using Graph Neural Networks
<p>Contains simulation results of the forward displacement from beginning to end-diastole for approximately 3000 synthetically generated left ventricle geometries.</p> <p>The simulation results are split into training, validation and test data.</p> <p>The data is described in detail in a forthcoming publication in <em>Computer Methods in Applied Mechanics and Engineering</em> - further information will be provided upon publication. A GitHub repository will also be made available, with code for processing the simulation data and training a Graph Neural Network emulator.</p>
DeepSelectNet: Deep Neural Network Based Selective Sequencing for Oxford Nanopore Sequencing
<p>Curated dataset for the manuscript named "DeepSelectNet: Deep Neural Network Based Selective Sequencing for Oxford Nanopore Sequencing".</p> <p>Five publicly available datasets sequenced on ONT MinION/GridION were used for the experiments (see below for original sources). These datasets contained raw signal data in single-FAST5 format (one file per each read), which were converted to BLOW5 format using slow5tools to enable convenient and efficient file manipulation. Then, 40,000 reads containing at least 4500 signal samples were extracted from each dataset. From each dataset, 20,000 reads are for training (<species>/train-<species>.blow5) and the rest for testing (<species>/test-<species>.blow5). Basecalled reads for the dataset used for testing are also available (test-<species>.fastq). Guppy version 6.1.3 under dna_r9.4.1_450bps_hac mode was used. The reference genomes are also given (<species>/<species>-ref.fasta)</p> <p>Original datasets are from the following sources:<br> SARS-CoV-2: https://community.artic.network/t/links-to-raw-fast5-fastq-data-for-artic-protocol/17<br> Zymo Metagenome: https://github.com/LomanLab/mockcommunity<br> Chlamydomonas: https://sra-download.ncbi.nlm.nih.gov/traces/era20/ERZ/003237/ERR3237140/Chlamydomonas_0.tar.gz<br> Saccharomyces cerevisiae: https://www.ncbi.nlm.nih.gov/bioproject/PRJNA510813</p>
Neural network for Lithium Metal Battery
<p>Electric cars are an integral part of our clean energy future – every time one replaces a gas-powered vehicle, it can save 1.5 tons of carbon dioxide per year. But to truly expand the population and reach of electric cars, new energy storage solutions must be developed to produce lighter vehicles with longer ranges and more powerful batteries.</p> <p>A team of researchers from Lawrence Berkeley National Laboratory (Berkeley Lab) and UC Irvine recently moved this effort forward with the development of deep-learning algorithms to automate the quality control and assessment of new battery designs.</p> <p>The research team, led by Berkeley Lab’s Daniela Ushizima, a staff scientist in the Applied Mathematics and Computational Research Division and a Berkeley Institute for Data Science Research Affiliate, includes scientists from the National Fuel Cell Research Center (NFRC) at UC Irvine and collaborators from UC Berkeley’s Department of Electrical Engineering and Computer Sciences and School of Information. Together, they created these deep-learning algorithms to automate the inspection of batteries with data acquired using advanced instruments, including those at Berkeley Lab’s Advanced Light Source (ALS). By using X-ray tomography as the input data, as well as prototypes defined by battery experts, the research team developed automated methods to detect battery defects in rechargeable lithium metal batteries and measure their growth during battery cycling.</p> <p>The researchers focused on solid-state lithium metal batteries (LMB), which are different from traditional lithium-ion batteries in that they use solid electrodes and electrolytes, providing superior electrochemical performance and high energy density. Some of the challenges of this new technology are predicting battery cycling stability and preventing the formation of lithium dendrite growth, Ushizima noted. This harmful phenomenon may occur during LMB charge and discharge, when lithium can deposit irregularly, building up dendrites (lithium plating) that lead to failures, such as short-circuiting. These morphologies are key to the LMB quality, and they can be captured and analyzed using X-ray microtomography (XRT) scans. Machine learning algorithms and multiscale representation of XRT from LMB samples enable the quantification of LMB defects.</p>
Estimation of axial loads in tie-rods: Dataset generated from Finite Element simulations for training Artificial Neural Network
<p>Dataset employed for training the Artificial Neural Networks (ANNs) presented in the cited journal article. The trained ANNs were used to estimate the tensile force in tie-rods installed in a historical structure (the church of the monastery of Sant Cugat close to Barcelona) from dynamic parameters obtained from vibration testing.</p> <p>The dataset consists of input-otput data generated using finite element (FE) simulations. A blank column has been used to separate input data from output data.</p> <p>More details on the nature of the data and how it was employed can be found in the following journal article, which is supplemented by this upload:<br> <em><strong>Makoond N, Pelà L, Molins C. Robust estimation of axial loads sustained by tie-rods in historical structures using Artificial Neural Networks. Structural Health Monitoring. 2022;0(0). doi:</strong></em><strong><a href="https://doi.org/10.1177/14759217221123326">10.1177/14759217221123326</a></strong></p> <p><a href="https://www.researchgate.net/publication/364098652_Robust_estimation_of_axial_loads_sustained_by_tie-rods_in_historical_structures_using_Artificial_Neural_Networks">Link to author's version of accepted manuscript</a></p> <p>This work was supported by the Servei del Patrimoni Arquitectònic of the Generalitat de Catalunya through a project (managed by the City Council of Sant Cugat) aimed at monitoring the church of the Monastery of Sant Cugat (grant number C-10764). Financial support is also acknowledged from the Ministry of Science, Innovation and Universities of the Spanish Government and the ERDF (European Regional Development Fund) through the SEVERUS project (Multilevel evaluation of seismic vulnerability and risk mitigation of masonry buildings in resilient historical urban centres) (grant number RTI2018-099589-B-I00).</p>
Data from: Domain-specific neural networks improve automated bird sound recognition already with small amount of local data
<p><span><span>An automatic bird sound recognition system is a useful tool for collecting data of different bird species for ecological analysis. Together with autonomous recording units (ARUs), such a system provides a possibility to collect bird observations on a scale that no human observer could ever match. During the last decades progress has been made in the field of automatic bird sound recognition, but recognizing bird species from untargeted soundscape recordings remains a challenge. <br></span></span></p> <p><span><span>In this article we demonstrate the workflow for building a global identification model and adjusting it to perform well on the data of autonomous recorders from a specific region. We show how data augmentation and a combination of global and local data can be used to train a convolutional neural network to classify vocalizations of 101 bird species. We construct a model and train it with a global data set to obtain a base model. The base model is then fine-tuned with local data from Southern Finland in order to adapt it to the sound environment of a specific location and tested with two data sets: one originating from the same Southern Finnish region and another originating from a different region in German Alps.<br></span></span></p> <p><span><span>Our results suggest that fine-tuning with local data significantly improves the network performance. Classification accuracy was improved for test recordings from the same area as the local training data (Southern Finland) but not for recordings from a different region (German Alps). Data augmentation enables training with a limited number of training data and even with few local data samples significant improvement over the base model can be achieved. Our model outperforms the current state-of-the-art tool for automatic bird sound classification.<br></span></span></p> <p><span><span>Using local data to adjust the recognition model for the target domain leads to improvement over general non-tailored solutions. The process introduced in this article can be applied to build a fine-tuned bird sound classification model for a specific environment.</span></span></p>
Exoplanet atmosphere evolution: emulation with neural networks: supplementary data
<p>Supplementary data for 'Exoplanet atmosphere evolution: emulation with neural networks'. Includes MCMC chain for Bayesian Hierarchical Model (BHM) including samples of core mass for all planets, as well 5 hyper parameters (see paper for details). Additionally, a machine readable version of Table 1 is made available.</p>
Figure 5 in Evaluation of geostatistical method and hybrid Artificial Neural Network with imperialist competitive algorithm for predicting distribution pattern of Tetranychus urticae (Acari: Tetranychidae) in cucumber field of Behbahan, Iran
Figure 5. Moving colonies to imperialist in culture and language axes (AtashpazGargari et al. 2008).
Figure 2 in Evaluation of geostatistical method and hybrid Artificial Neural Network with imperialist competitive algorithm for predicting distribution pattern of Tetranychus urticae (Acari: Tetranychidae) in cucumber field of Behbahan, Iran
Figure 2. Generalized semivariogram showing the range of spatial dependence, nugget effect (C0) variability associated with spatial dependence (C), and sill (C + C0).
ScienceDex guides
Understand access before you commit
These curated guides explain access requirements, typical timelines, costs, and reuse considerations for widely used research datasets.
Allen Brain Atlas
Allen Brain Atlas is an Allen Institute collection of brain map atlases, datasets, APIs, and analysis tools covering mouse, human, and non-human primate brain resources.
Annotated Behaviour and Observability Dataset (ABODe)
ABODe is a University of Edinburgh DataShare dataset for behavior classification in group-housed mice using home-cage video, identities, bounding boxes, ground-plate positions, and annotator labels.
DANDI Archive for NWB datasets
DANDI is a BRAIN Initiative archive for publishing and sharing neurophysiology data, including electrophysiology, optophysiology, and behavioral data packaged as NWB and related standards.
International Brain Laboratory public data
The International Brain Laboratory public data releases expose standardized mouse decision-making experiments, including Neuropixels recordings, widefield calcium imaging, behavior, and session metadata accessed through the ONE API.
OpenNeuro
OpenNeuro is a free, open platform for sharing neuroimaging datasets, with public search, dataset pages, and download paths for web, S3, DataLad, and the OpenNeuro CLI.